© 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. 35971
    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
    ؘ
    1.30
    دی
    1.25
    סה
    1.25
    د
    1.24
    вости
    1.23
     Ở
    1.23
     הרו
    1.23
     따르면
    1.21
    Count
    1.20
    the
    1.20
    POSITIVE LOGITS
    ला
    1.61
    א
    1.57
    ता
    1.54
     Consultado
    1.49
    🥔
    1.49
    }$
    1.48
    €™
    1.41
    τα
    1.39
    ，
    1.39
    ן
    1.39
    Activations Density 0.002%

    No Known Activations