© 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. 3591
    Prev
    Next
    INDEX
    Explanations

    .com, .org, .s

    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
    $[\
    0.07
     similarity
    0.07
     वसूली
    0.07
     parentheses
    0.07
    貥
    0.07
     विरोध
    0.07
    testers
    0.07
     similarities
    0.07
    Җ
    0.07
    ρών
    0.07
    POSITIVE LOGITS
    7
    0.06
    d
    0.06
    вно
    0.06
    gmail
    0.06
    0
    0.06
    8
    0.06
    possibly
    0.06
    3
    0.06
     sketchy
    0.06
    래
    0.06
    Activations Density 0.030%

    No Known Activations