© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11675
    Prev
    Next
    INDEX
    Explanations

    words that are positive adjectives

    oai_token-act-pair · gemini-2.0-flash

    terms related to roles and titles

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

    strong supporters

    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
    ftagPool
    -0.75
    $_['
    -0.74
     itſelf
    -0.73
    SerializedName
    -0.70
     مشين
    -0.66
     endblock
    -0.65
    Parcelize
    -0.65
    RectangleBorder
    -0.61
    Sucesor
    -0.61
     aveug
    -0.60
    POSITIVE LOGITS
    HideFlags
    0.54
     Fuller
    0.49
     part
    0.47
     spokesman
    0.47
    ietf
    0.47
     collaboration
    0.46
     viewer
    0.45
    שת
    0.43
     Thayer
    0.42
     spokeswoman
    0.41
    Activations Density 1.156%

    No Known Activations