© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149783
    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_23_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
     bhikkhu
    0.46
     MHK
    0.45
    的机会
    0.43
    蠵
    0.41
    <0x00>
    0.41
     යුතුය
    0.41
    ەکە
    0.40
    杀
    0.40
    馍
    0.40
     Prothorax
    0.39
    POSITIVE LOGITS
    Fram
    0.37
     Ryd
    0.37
    Carlo
    0.35
    ρικ
    0.35
    立て
    0.35
    ρύ
    0.35
    anesi
    0.35
    тному
    0.35
     கும
    0.34
    atud
    0.34
    Activations Density 0.000%

    No Known Activations