© 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. 8511
    Prev
    Next
    INDEX
    Explanations

    the word 'now', and pronouns and auxiliary verbs adjacent to it

    oai_token-act-pair · gemini-2.0-flash

    present participles and action words

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

    Now

    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
     Réponses
    -0.68
    躇
    -0.62
     مشين
    -0.59
    ";}
    -0.59
    RetentionPolicy
    -0.57
     المعيارى
    -0.56
     disambiguazione
    -0.56
    "]}
    -0.56
     NIP
    -0.56
    DoubleQuotes
    -0.55
    POSITIVE LOGITS
     joining
    0.54
     roll
    0.52
     invokingState
    0.50
    setColumns
    0.49
     making
    0.49
     khiến
    0.49
     doing
    0.49
     per
    0.49
     that
    0.48
    setLevel
    0.48
    Activations Density 11.801%

    No Known Activations