© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3533
    Prev
    Next
    INDEX
    Explanations

    movement, scene, community, system, skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    0.29
    an
    0.28
    sect
    0.25
    on
    0.25
    ни
    0.23
     metá
    0.22
    of
    0.22
     aggression
    0.22
    to
    0.21
     culmin
    0.21
    POSITIVE LOGITS
    ohr
    0.27
    ดา
    0.26
    ancji
    0.24
     företag
    0.24
    emeen
    0.23
    籵
    0.23
    
    0.23
    veloppement
    0.23
     protože
    0.23
     april
    0.23
    Activations Density 0.425%

    No Known Activations