© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88288
    Prev
    Next
    INDEX
    Explanations

    um

    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_60_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
    m
    0.87
    at
    0.75
    م
    0.53
    in
    0.48
    os
    0.42
    nije
    0.41
     purnama
    0.41
    atlar
    0.40
    ნი
    0.40
    muy
    0.40
    POSITIVE LOGITS
    t
    0.56
    es
    0.51
    z
    0.49
    tur
    0.48
    ing
    0.47
    tale
    0.47
    especially
    0.46
    eg
    0.46
    edi
    0.46
    tura
    0.45
    Activations Density 0.000%

    No Known Activations