© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134724
    Prev
    Next
    INDEX
    Explanations

    phenotypic variation, modulation, aspect

    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_1_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
    t
    2.02
    am
    1.27
    y
    1.27
    i
    1.09
    <0x80>
    1.06
    い
    1.05
    e
    1.04
    あ
    1.04
    いち
    1.03
    tive
    1.02
    POSITIVE LOGITS
    ों
    1.41
     on
    1.29
     to
    1.17
     at
    1.13
     a
    0.96
     (
    0.95
    ы
    0.95
    ler
    0.94
    ।
    0.94
    。",
    0.94
    Activations Density 0.001%

    No Known Activations