© 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. 92962
    Prev
    Next
    INDEX
    Explanations

    hom

    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
     مە
    0.51
     M
    0.49
     म
    0.46
     m
    0.44
     М
    0.44
    m
    0.44
     União
    0.43
     ESD
    0.42
     م
    0.41
    inins
    0.41
    POSITIVE LOGITS
     schizophren
    0.71
     antipsych
    0.71
     psychosis
    0.70
     schizophrenia
    0.70
     psychotic
    0.60
     morphological
    0.43
    镍
    0.41
    泄漏
    0.40
     threats
    0.39
     frustrations
    0.39
    Activations Density 0.000%

    No Known Activations