© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4546
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    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
    e
    1.08
    ET
    0.98
    TACT
    0.98
    𝙚
    0.98
    ого
    0.96
     Assessing
    0.95
    ó
    0.95
     món
    0.94
    oon
    0.93
    oz
    0.93
    POSITIVE LOGITS
    ны
    1.04
    <?>
    1.03
    用紙
    1.02
    И
    1.02
    usuarios
    0.98
    મ
    0.98
    musical
    0.97
    름
    0.96
    쬐
    0.96
    zeitig
    0.96
    Activations Density 0.000%

    No Known Activations