© 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. 14491
    Prev
    Next
    INDEX
    Explanations

    eclipse

    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
     ades
    0.47
     dj
    0.44
     lungo
    0.44
     sulit
    0.41
    फोल
    0.41
     Gifts
    0.41
     tattha
    0.40
    উ
    0.40
    不断
    0.40
     Drinks
    0.40
    POSITIVE LOGITS
    रेज
    0.52
    CLM
    0.47
    стым
    0.46
    नियों
    0.45
    delete
    0.44
    менный
    0.43
    dés
    0.43
    راحی
    0.43
    Mé
    0.42
    duction
    0.42
    Activations Density 0.017%

    No Known Activations