Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 245305
    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
    arrêter
    1.27
     otros
    1.27
     Dateien
    1.24
     arrêter
    1.24
    jTextField
    1.24
     kırmızı
    1.23
     oldal
    1.23
    $-\
    1.21
     altres
    1.21
     weer
    1.20
    POSITIVE LOGITS
    ission
    1.01
     Belly
    1.01
     Stam
    0.98
    ौसी
    0.97
     Cat
    0.96
     paint
    0.94
    ert
    0.94
     **
    0.89
    Paint
    0.89
     Specialized
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.