© 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. 7909
    Prev
    Next
    INDEX
    Explanations

    mentions of years, especially those starting with "1" and "9." It sometimes also returns other adjacent nouns and verbs.

    oai_token-act-pair · gemini-2.0-flash

    1

    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
    1
    -0.49
    <bos>
    -0.45
     дя
    -0.44
    me
    -0.44
    '
    -0.41
    '=>'
    -0.39
    ım
    -0.39
    re
    -0.38
    -------
    -0.38
     =
    -0.37
    POSITIVE LOGITS
    8
    0.78
     eighty
    0.75
     Eighty
    0.73
    RenderAtEndOf
    0.72
    󠁴
    0.71
    9
    0.69
    ⁸
    0.68
     ninety
    0.66
    httphttps
    0.63
    ighty
    0.63
    Activations Density 6.051%

    No Known Activations