© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37298
    Prev
    Next
    INDEX
    Explanations

    scrubbing something clean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    )+
    0.61
    zt
    0.59
    Financial
    0.59
    Ҭ
    0.58
    HIST
    0.57
    '));
    0.56
     والف
    0.56
     e
    0.55
     been
    0.54
     });
    0.54
    POSITIVE LOGITS
    čke
    0.64
    ியம்
    0.63
    हां
    0.61
    囍
    0.59
     επα
    0.57
    mateurs
    0.55
     cellulite
    0.55
    ōn
    0.55
    ämme
    0.55
    exe
    0.54
    Activations Density 0.001%

    No Known Activations