© 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. 157725
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     a
    1.20
    ை
    1.07
    <0x80>
    1.03
    ン
    0.99
     appelée
    0.95
    न
    0.93
    ст
    0.91
     œuvres
    0.91
    री
    0.90
     by
    0.90
    POSITIVE LOGITS
    。
    1.21
    ।
    1.14
    c
    1.07
     is
    1.05
    g
    1.04
    к
    1.03
    חר
    1.02
    на
    0.93
    с
    0.93
    的時間
    0.90
    Activations Density 0.000%

    No Known Activations