© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2200
    Prev
    Next
    INDEX
    Explanations

    words that relate to acting roles in television and film

    oai_token-act-pair · gemini-2.0-flash

    references to "part" or sections

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

    part

    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
     ostavi
    -0.60
    ')")
    -0.59
    abetes
    -0.58
    AnchorStyles
    -0.54
     समीक्षाओं
    -0.51
     getApp
    -0.50
    󠁿
    -0.48
    tvguidetime
    -0.48
     Reproduce
    -0.47
    BagConstraints
    -0.46
    POSITIVE LOGITS
     part
    0.67
    Часть
    0.66
    TypedDataSet
    0.65
    Part
    0.64
     lead
    0.61
     parts
    0.60
    part
    0.59
     Part
    0.58
     PART
    0.56
     localObject
    0.56
    Activations Density 2.865%

    No Known Activations