© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5410
    Prev
    Next
    INDEX
    Explanations

    end confirmation

    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_3_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
     gericht
    0.52
    უქ
    0.51
     Laurie
    0.51
    publique
    0.50
     textured
    0.50
    𝗺
    0.49
    ringstream
    0.49
     dolu
    0.48
    ationale
    0.48
    ອບ
    0.48
    POSITIVE LOGITS
    d
    0.66
    g
    0.64
    c
    0.56
     instill
    0.56
    is
    0.52
     וח
    0.51
    e
    0.51
     গ্রহণযোগ্য
    0.50
    etag
    0.49
    ન
    0.49
    Activations Density 1.945%

    No Known Activations