© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49367
    Prev
    Next
    INDEX
    Explanations

    negative qualities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     unt
    0.47
    פן
    0.37
     Unt
    0.35
    late
    0.35
    軎
    0.35
     select
    0.34
     logically
    0.34
    眎
    0.34
     late
    0.33
     diar
    0.33
    POSITIVE LOGITS
     complicada
    0.42
     mindre
    0.39
    あえず
    0.38
     less
    0.38
     Strugg
    0.38
    constrained
    0.37
     impaired
    0.37
     ஒன்றாக
    0.36
     informativa
    0.36
    たくさんの
    0.36
    Activations Density 0.020%

    No Known Activations