© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245627
    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_11_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
     Tur
    1.00
     autant
    0.96
     Finnish
    0.93
    景
    0.91
     mengak
    0.90
     Vali
    0.89
     ovih
    0.88
     dell
    0.87
     Inhalte
    0.87
    쿱
    0.86
    POSITIVE LOGITS
    𝗦
    1.29
    ﺘ
    1.19
    緣
    1.10
    ड्डा
    1.10
    say
    1.08
    ுகிறது
    1.07
    ഷേ
    1.06
    is
    1.05
    ResumeLayout
    1.04
    ᆞ
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.