© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161236
    Prev
    Next
    INDEX
    Explanations

    euclid, euphony, euforia, citizen, blue, phoria

    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_2_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
     are
    1.40
    ı
    1.16
    ש
    1.07
    ری
    1.04
     array
    1.02
    ী
    0.98
     這
    0.96
    ="
    0.95
    个
    0.93
     out
    0.92
    POSITIVE LOGITS
    d
    1.19
    ig
    1.09
    ných
    1.05
    ↵
    1.04
    Z
    1.03
    тят
    1.02
    ığı
    1.02
    고
    1.01
    dien
    0.99
    ت
    0.96
    Activations Density 0.000%

    No Known Activations