© 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. 163594
    Prev
    Next
    INDEX
    Explanations

    on the table

    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
     saat
    0.53
     bodyguard
    0.50
    h
    0.50
     high
    0.49
     :
    0.49
     much
    0.48
     body
    0.48
     Film
    0.48
     regional
    0.47
     film
    0.46
    POSITIVE LOGITS
    atá
    0.50
    دست
    0.48
    Ꮘ
    0.48
    ੰ
    0.46
     Crosby
    0.45
    افي
    0.45
    мад
    0.45
    ət
    0.44
     Crowe
    0.44
    ୂ
    0.44
    Activations Density 0.001%

    No Known Activations