© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256780
    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
    or
    1.29
    x
    1.15
    és
    1.09
     else
    1.02
    ри
    1.01
    ర్
    0.98
    are
    0.98
    h
    0.95
    in
    0.94
    х
    0.92
    POSITIVE LOGITS
     obdob
    1.43
    การ
    1.37
     порядка
    1.37
     ficando
    1.36
    一个
    1.35
    ટી
    1.34
    ان
    1.33
    aciones
    1.32
     tercer
    1.32
    हमारी
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.