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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15551
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with groups, churches, or authority.

    oai_token-act-pair · gemini-2.0-flash

    religion/churches

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     convention
    -0.58
    Datuak
    -0.56
     Convention
    -0.56
    Convention
    -0.54
    下载附件
    -0.51
    ticons
    -0.50
     unknownFields
    -0.49
     AssemblyCulture
    -0.48
     conventions
    -0.47
     CURIAM
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.63
     agricoles
    0.60
     peines
    0.58
    তথ্যসূত্র
    0.56
    eramente
    0.56
    umą
    0.55
     Finlay
    0.55
    fscanf
    0.54
     Ephesus
    0.53
     juridiques
    0.53
    Activations Density 4.790%

    No Known Activations