© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197901
    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_4_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
    1.04
    )
    0.93
    ier
    0.91
    یر
    0.90
    '
    0.89
    g
    0.88
    c
    0.88
    al
    0.84
    ’
    0.84
    in
    0.84
    POSITIVE LOGITS
    .
    1.02
    0.93
    IS
    0.91
    ة
    0.86
     Sicht
    0.84
     be
    0.80
    EST
    0.79
     Öffentlich
    0.79
    వరి
    0.77
    ্ষ
    0.77
    Activations Density 0.000%

    No Known Activations