© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139413
    Prev
    Next
    INDEX
    Explanations

    % specifiers

    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_37_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
     आकाश
    0.39
     Diary
    0.38
    nab
    0.37
    oxylated
    0.37
     秋
    0.37
     journal
    0.36
     subdivision
    0.35
     ipotesi
    0.35
    ensioni
    0.35
    ြ
    0.35
    POSITIVE LOGITS
     Intra
    0.46
     Moulin
    0.43
     intra
    0.43
    ure
    0.41
    तरी
    0.38
    intra
    0.38
    דיה
    0.38
    Hol
    0.37
     تر
    0.37
    被害
    0.36
    Activations Density 0.000%

    No Known Activations