© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260781
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    に
    1.13
    ر
    1.05
    ці
    1.01
    心情
    0.97
    ć
    0.96
    ть
    0.95
    ર
    0.95
    وں
    0.94
    ರ
    0.93
    на
    0.91
    POSITIVE LOGITS
     HBO
    1.21
     obscene
    1.10
     adultery
    1.06
    traction
    1.02
     redu
    1.02
     homestead
    1.02
     imput
    1.02
     addiction
    1.01
     TLC
    1.01
     antisocial
    1.01
    Activations Density 0.000%

    No Known Activations