© 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. 3540
    Prev
    Next
    INDEX
    Explanations

    windows search bar

    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
    й
    2.47
    ी
    1.87
    tiered
    1.63
     comple
    1.51
    altra
    1.51
     Odyssey
    1.46
    कर्ता
    1.36
    料理
    1.36
    зва
    1.33
    incidence
    1.33
    POSITIVE LOGITS
     estadounid
    2.06
    ل
    1.99
     oxalic
    1.87
    totime
    1.83
    ෂ්
    1.81
    ت
    1.79
    jän
    1.79
    ető
    1.77
    咤
    1.77
    ılık
    1.74
    Activations Density 0.000%

    No Known Activations