© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9448
    Prev
    Next
    INDEX
    Explanations

    words which are short, common, and connect nearby concepts and actors

    oai_token-act-pair · gemini-2.0-flash

    legal/governmental proceedings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    (!__
    -0.80
    NameInMap
    -0.79
    providedIn
    -0.77
     للمعارف
    -0.76
    DeleteBehavior
    -0.72
     Theſe
    -0.72
     raiſ
    -0.71
    Sklici
    -0.69
     Процитовано
    -0.69
     estekak
    -0.69
    POSITIVE LOGITS
    ok
    0.40
    被告
    0.38
    y
    0.37
     Baus
    0.36
    για
    0.36
    ap
    0.36
     G
    0.36
     запас
    0.35
    supset
    0.35
    MathML
    0.35
    Activations Density 4.649%

    No Known Activations