© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2677
    Prev
    Next
    INDEX
    Explanations

    band

    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_40_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
     FontWeight
    0.41
    UCS
    0.39
    Wal
    0.38
    Неза
    0.38
    ev
    0.36
     MCS
    0.36
    Conte
    0.36
    {|\
    0.35
    朗
    0.35
    傍
    0.35
    POSITIVE LOGITS
    band
    0.66
     band
    0.59
     banda
    0.56
    Band
    0.53
     Band
    0.52
     banding
    0.49
     Bandar
    0.49
     bands
    0.48
     Bande
    0.48
    バンド
    0.47
    Activations Density 0.096%

    No Known Activations