© 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. 12743
    Prev
    Next
    INDEX
    Explanations

    modal verbs such as could, might, and should

    oai_token-act-pair · gemini-2.0-flash

    modal verbs indicating potentiality

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

    possibility or speculation

    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
     createSlice
    -0.57
    äfts
    -0.56
    Bronnen
    -0.55
    Autoritní
    -0.53
     tolerate
    -0.53
     Colle
    -0.53
     Harcourt
    -0.52
     Arka
    -0.52
     Kool
    -0.52
    VersionUID
    -0.52
    POSITIVE LOGITS
     صوتيه
    0.69
    GraphicsUnit
    0.60
    ContentAsync
    0.56
     søndag
    0.53
     paljon
    0.53
     jadx
    0.51
     snart
    0.51
    KURZBESCHREIBUNG
    0.50
     fácilmente
    0.48
    TimeInterval
    0.48
    Activations Density 0.886%

    No Known Activations