© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9113
    Prev
    Next
    INDEX
    Explanations

    elements of a website, including menu options and code snippets

    oai_token-act-pair · gemini-2.0-flash

    non-english, code, errors

    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
    ]='\
    -0.80
     Мексичка
    -0.73
     gynhyrchwyd
    -0.73
    iffance
    -0.71
    ]--;
    -0.64
     Italijanski
    -0.63
     Италијани
    -0.63
    writeFieldEnd
    -0.63
    asantry
    -0.63
    citroën
    -0.62
    POSITIVE LOGITS
    s
    0.90
    m
    0.89
    v
    0.88
    g
    0.83
    u
    0.83
    in
    0.82
    te
    0.80
    li
    0.79
    l
    0.79
    y
    0.79
    Activations Density 0.039%

    No Known Activations