© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79479
    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_0_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
    <0xBD>
    0.59
    се
    0.49
    ↵
    0.49
    aves
    0.47
    -
    0.47
    ah
    0.46
     Wildlife
    0.46
    uci
    0.46
    getter
    0.46
     Pestic
    0.45
    POSITIVE LOGITS
    ي
    0.80
    い
    0.78
    ம்
    0.70
    י
    0.68
    Okay
    0.60
    した
    0.59
     meaningfully
    0.58
    つ
    0.58
    માં
    0.57
    値を
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.