© 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. 257022
    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
    ்
    0.97
    erns
    0.94
     Cahill
    0.91
     حد
    0.90
    אר
    0.89
    घव
    0.88
    Hvis
    0.88
    ത്തരം
    0.87
     updater
    0.87
     corred
    0.85
    POSITIVE LOGITS
     мощность
    1.47
    ный
    1.41
     foothold
    1.33
     débar
    1.30
    𝘼
    1.29
    Ⅶ
    1.29
    ozygous
    1.27
     quit
    1.27
    targeted
    1.27
    inase
    1.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.