© 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. 44510
    Prev
    Next
    INDEX
    Explanations

    recent

    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
     comenc
    0.68
    お金
    0.66
     недо
    0.64
     θε
    0.64
     αυτές
    0.64
    o
    0.63
     сво
    0.63
    a
    0.63
    don
    0.62
     лист
    0.62
    POSITIVE LOGITS
    人
    0.96
    ৬
    0.86
    ת
    0.86
    وم
    0.84
    о
    0.84
    ية
    0.82
    ен
    0.80
    ম
    0.80
    ем
    0.77
    কে
    0.76
    Activations Density 0.001%

    No Known Activations