© 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-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57014
    Prev
    Next
    INDEX
    Explanations

    particularly + strong preference/attribute

    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
    шти
    0.66
     다르
    0.65
    Depuis
    0.65
    КА
    0.64
     únicas
    0.63
    electrons
    0.62
    ת
    0.61
    濯
    0.61
    Due
    0.61
     खिलाड़ियों
    0.61
    POSITIVE LOGITS
    };
    0.67
    _
    0.60
     bv
    0.57
    }
    0.57
    );
    0.56
    ye
    0.54
    nt
    0.54
    g
    0.53
     vou
    0.52
     aunt
    0.52
    Activations Density 0.003%

    No Known Activations