© 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. 107250
    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
    c
    1.45
     you
    1.34
     this
    1.20
    H
    1.14
    W
    1.12
    S
    1.11
    ש
    1.11
    ある
    1.06
    you
    1.06
    K
    1.06
    POSITIVE LOGITS
    inį
    0.93
    toDate
    0.91
    тэ
    0.87
    фии
    0.86
    нні
    0.85
    снов
    0.82
     convirtió
    0.82
    Jähr
    0.82
    вому
    0.81
    Passwords
    0.81
    Activations Density 0.000%

    No Known Activations