© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109133
    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
    то
    1.50
    to
    1.38
    ார்
    1.16
    ோ
    1.10
    ра
    1.09
    стите
    1.06
    ু
    1.02
    <0x80>
    1.02
    сти
    1.02
    ты
    1.02
    POSITIVE LOGITS
     an
    1.20
    ك
    1.11
     the
    1.09
    8
    1.07
    !
    1.06
    O
    0.97
     sozial
    0.95
    nw
    0.93
     not
    0.92
     build
    0.90
    Activations Density 0.000%

    No Known Activations