© 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-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5273
    Prev
    Next
    INDEX
    Explanations

    Isolde Finch

    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
    ranger
    1.15
    an
    1.02
    is
    0.97
    rater
    0.96
    arme
    0.96
     recién
    0.95
    a
    0.94
    he
    0.93
    u
    0.93
    et
    0.91
    POSITIVE LOGITS
    м
    1.19
     marred
    1.17
     conceivably
    1.14
     SQLException
    1.13
    一个
    1.12
    recv
    1.12
    toolStrip
    1.10
     readline
    1.10
    Ironically
    1.07
     thumbnailUrl
    1.06
    Activations Density 0.001%

    No Known Activations