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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 335
    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_24_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
     OXIDES
    0.73
    TOOL
    0.67
    Plaintiff
    0.67
    慚
    0.65
    //
    0.64
    VER
    0.63
     adhesions
    0.63
     deltaTime
    0.63
    课
    0.63
    PROJECT
    0.62
    POSITIVE LOGITS
    al
    1.00
    し
    0.81
     macht
    0.77
    comend
    0.77
     nü
    0.77
     bistro
    0.76
    nicht
    0.76
    াদিগকে
    0.75
     upper
    0.75
    ğı
    0.75
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.