© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231304
    Prev
    Next
    INDEX
    Explanations

    Spectra light and shows

    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_6_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
    u
    1.10
    و
    0.89
     Besonders
    0.77
    their
    0.76
     који
    0.75
    सँग
    0.74
     majú
    0.74
    the
    0.74
    다
    0.73
    지만
    0.72
    POSITIVE LOGITS
    ut
    0.96
    of
    0.95
    ре
    0.85
     KPIs
    0.84
    0.84
    ри
    0.82
    י
    0.82
    lam
    0.81
    一
    0.81
    アス
    0.78
    Activations Density 0.000%

    No Known Activations