© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6808
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and notation

    oai_token-act-pair · gemini-2.0-flash

    math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    );}
    -0.98
    '}>
    -0.96
    ).}
    -0.96
    .)}
    -0.95
    ագրություններ
    -0.91
    )».
    -0.88
    ";}
    -0.85
    )”.
    -0.85
    "}>
    -0.82
    )</
    -0.81
    POSITIVE LOGITS
     zoveel
    0.49
    ::_
    0.47
     vostri
    0.47
    rmi
    0.44
    GraphicsUnit
    0.44
    st
    0.44
    sendTo
    0.42
    ao
    0.42
    Focus
    0.42
     sm
    0.42
    Activations Density 14.468%

    No Known Activations