© 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. 4340
    Prev
    Next
    INDEX
    Explanations

    list items that start with a number

    oai_token-act-pair · gemini-2.0-flash

    numeric values and actions

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

    numbers

    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
    ConstraintMaker
    -0.84
    Autoritní
    -0.77
     unknownFields
    -0.73
    SourceChecksum
    -0.72
    tagHelperRunner
    -0.72
     Paglinawan
    -0.72
    drawal
    -0.71
     CURIAM
    -0.70
    hematical
    -0.70
    FieldBuilder
    -0.69
    POSITIVE LOGITS
    .
    0.72
    ViewChild
    0.39
     المعيارى
    0.37
    points
    0.36
    ali
    0.35
    enderror
    0.35
    A
    0.35
    ceğim
    0.35
    E
    0.35
     points
    0.34
    Activations Density 1.735%

    No Known Activations