© 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. 133875
    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_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
     werewolf
    1.28
     in
    1.18
    }
    1.17
     was
    1.15
    ي
    1.14
    ы
    1.13
    น
    1.09
     heavyweight
    1.08
    ม
    1.08
     die
    1.07
    POSITIVE LOGITS
    t
    1.56
    '
    1.38
    ai
    1.34
    لی
    1.20
    g
    1.18
    c
    1.13
    ds
    1.09
    kval
    1.09
    ent
    1.07
    tio
    1.02
    Activations Density 0.000%

    No Known Activations