© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123538
    Prev
    Next
    INDEX
    Explanations

    student model, role, comics

    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_3_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
     كه
    0.72
    }$
    0.69
    ס
    0.68
    3
    0.67
    1
    0.66
    রা
    0.62
    lara
    0.62
    6
    0.62
    ៩
    0.61
     courte
    0.61
    POSITIVE LOGITS
    یاء
    0.68
    ണ്ടി
    0.63
     aulas
    0.62
    il
    0.61
     Strokes
    0.61
     Fungsi
    0.60
     있는
    0.59
    จะ
    0.59
     쉽게
    0.59
     मा
    0.58
    Activations Density 0.005%

    No Known Activations