© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23459
    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_56_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
    0.20
    0.20
     –
    0.19
    ites
    0.19
    man
    0.18
    BC
    0.18
    Up
    0.17
    PG
    0.17
    ans
    0.17
    Man
    0.17
    POSITIVE LOGITS
    <unused700>
    0.29
    <unused1890>
    0.28
    <unused487>
    0.26
     एक्सयर
    0.26
    <unused389>
    0.26
    <unused99>
    0.26
     ditu
    0.26
    <unused1132>
    0.26
    <unused383>
    0.25
    <unused459>
    0.25
    Activations Density 0.000%

    No Known Activations