© 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. 6150
    Prev
    Next
    INDEX
    Explanations

    lines of code that have some indentations

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    3
    -0.94
    .³
    -0.92
     three
    -0.90
     ketiga
    -0.82
    trois
    -0.81
     trois
    -0.79
     troisième
    -0.77
     uſed
    -0.77
     Efq
    -0.77
     ③
    -0.77
    POSITIVE LOGITS
     ***!
    0.61
    2
    0.57
     
    0.56
    Fifth
    0.52
     Fifth
    0.52
    fifth
    0.50
    four
    0.50
    </
    0.50
    ("")]
    0.49
    0.49
    Activations Density 3.939%
    No Known Activations