© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13042
    Prev
    Next
    INDEX
    Explanations

    references to God and related religious concepts, especially in the context of personal connection and divine promise.

    oai_token-act-pair · gemini-2.0-flash

    words related to divine promise and support

    np_token-act-pair-logits · gpt-4o-mini

    religious textual analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.06
     gynhyrchwyd
    -0.91
     NSCoder
    -0.75
     hittar
    -0.69
    tagHelperRunner
    -0.68
    ThroughAttribute
    -0.68
     '\\;'
    -0.67
    AutoScaleMode
    -0.66
    MigrationBuilder
    -0.66
    DockStyle
    -0.63
    POSITIVE LOGITS
     set
    0.52
    sianic
    0.44
     moved
    0.44
    ttemberg
    0.41
     put
    0.41
     past
    0.41
    Rhestr
    0.41
     keep
    0.41
     place
    0.40
     repro
    0.40
    Activations Density 0.311%

    No Known Activations