© 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. 3987
    Prev
    Next
    INDEX
    Explanations

    the first two letters of the word "holiday"

    oai_token-act-pair · gemini-2.0-flash

    variations of "ho"

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

    laughter

    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
    matchCondition
    -0.68
    @[+][
    -0.61
     referenties
    -0.59
    aleg
    -0.56
    rrggbb
    -0.53
    tagHelperRunner
    -0.51
    DoubleQuotes
    -0.51
    ServiceName
    -0.51
    phytes
    -0.49
    Respuesta
    -0.48
    POSITIVE LOGITS
     étions
    0.55
     étoit
    0.53
    MeasureSpec
    0.53
     ModelExpression
    0.53
     Exactos
    0.52
    berdayakan
    0.52
     BoxDecoration
    0.51
    ValueGeneration
    0.51
     feroit
    0.51
    OGND
    0.51
    Activations Density 0.211%

    No Known Activations