© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162141
    Prev
    Next
    INDEX
    Explanations

    fragrant, flagrant, variant

    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_2_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
    מ
    1.38
    נ
    1.23
    ك
    1.14
    ス
    1.09
    מק
    1.04
    ف
    1.00
    その
    0.99
    เป็น
    0.98
    大
    0.97
    この
    0.96
    POSITIVE LOGITS
    n
    1.50
    et
    1.48
    on
    1.39
    νες
    1.30
    র
    1.30
    erd
    1.20
    o
    1.20
    is
    1.16
    eff
    1.13
    ig
    1.12
    Activations Density 0.000%

    No Known Activations