© 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. 3970
    Prev
    Next
    INDEX
    Explanations

    code snippets or code-related terms

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    InjectAttribute
    -0.78
    which
    -0.71
    ValueStyle
    -0.71
     but
    -0.69
    being
    -0.65
    }],
    -0.65
     виправивши
    -0.62
    but
    -0.60
    otherwise
    -0.60
     which
    -0.60
    POSITIVE LOGITS
    <bos>
    0.55
     CreateTagHelper
    0.51
    omena
    0.44
     excu
    0.43
     Paglinawan
    0.43
    onedDateTime
    0.41
    lename
    0.41
    äsident
    0.41
    getTimestamp
    0.41
    quina
    0.40
    Activations Density 2.202%

    No Known Activations