© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14892
    Prev
    Next
    INDEX
    Explanations

    proven results or ability

    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_13_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
    u
    0.53
    info
    0.48
    ୌ
    0.46
    ர
    0.44
     AND
    0.43
     rally
    0.43
    ents
    0.42
     स्त्री
    0.42
    ర్య
    0.40
     HOP
    0.40
    POSITIVE LOGITS
    ),”
    0.40
    )");
    0.38
    דות
    0.38
     grammaticality
    0.38
     tecnolog
    0.37
    льник
    0.37
    נם
    0.36
    ักษ
    0.36
    νης
    0.36
     ре
    0.35
    Activations Density 0.081%

    No Known Activations