© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204207
    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_6_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
    h
    1.31
    n
    1.17
    ad
    1.16
    in
    1.09
    il
    1.02
    ac
    1.01
    ма
    0.92
    adocia
    0.91
    as
    0.91
    ام
    0.90
    POSITIVE LOGITS
    '
    1.57
    ü
    1.05
    ’
    1.03
    ";
    1.01
    ется
    1.01
    “
    0.99
     wasn
    0.98
     iedere
    0.91
     was
    0.89
     gering
    0.89
    Activations Density 0.000%

    No Known Activations