© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46716
    Prev
    Next
    INDEX
    Explanations

    Hillside, House, Road, Cipher, Cop

    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
    dan
    0.81
    d
    0.64
    s
    0.60
    تو
    0.59
    direction
    0.59
    dari
    0.59
    tiba
    0.58
    distribution
    0.58
    dioxide
    0.58
    sin
    0.57
    POSITIVE LOGITS
    أ
    0.71
    أي
    0.66
    يلي
    0.65
    ে
    0.65
     miljoen
    0.62
    方法
    0.58
    内容
    0.57
    يير
    0.57
    高志森
    0.56
    إ
    0.56
    Activations Density 0.001%

    No Known Activations