© 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. 4415
    Prev
    Next
    INDEX
    Explanations

    a wide variety of keywords and short phrases including questions, brands, and child-related terms.

    oai_token-act-pair · gemini-2.0-flash

    animated content or cartoons

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

    kid shows series

    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
     ModelExpression
    -0.86
    FunctionFlags
    -0.68
     defaultstate
    -0.67
    Autoritní
    -0.66
    AddTagHelper
    -0.65
    ContentAsync
    -0.64
     Majefty
    -0.63
    rzost
    -0.62
    Datuak
    -0.60
    ="{{$
    -0.60
    POSITIVE LOGITS
    瀝
    0.50
     Cartoon
    0.46
     bar
    0.46
    letter
    0.45
     letter
    0.44
    timb
    0.44
    ConstraintMaker
    0.42
     Nick
    0.42
     Hanna
    0.41
     letters
    0.41
    Activations Density 1.471%

    No Known Activations