© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42379
    Prev
    Next
    INDEX
    Explanations

    alphanumeric identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     remarquable
    0.51
     pruned
    0.47
    ранд
    0.47
    ಪ್ಪು
    0.45
     концу
    0.44
    ᴺ
    0.42
     discretion
    0.42
     Dokl
    0.42
     တစ်
    0.41
     pegged
    0.41
    POSITIVE LOGITS
    ướ
    0.40
    fillRect
    0.39
    iber
    0.38
    ahiran
    0.37
    ⚽
    0.37
     배워
    0.37
    <start_of_image>
    0.37
     ادائیگی
    0.36
    uh
    0.36
     Corresponding
    0.36
    Activations Density 0.001%

    No Known Activations