© 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. 202020
    Prev
    Next
    INDEX
    Explanations

    preparations or steps

    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
    ۰
    1.31
    0
    1.04
    ם
    1.04
    <0x80>
    0.97
    INE
    0.95
     you
    0.93
    ,
    0.86
    нні
    0.85
    (
    0.84
     to
    0.83
    POSITIVE LOGITS
    К
    1.30
    е
    1.27
    كس
    1.16
    يل
    1.08
    g
    1.07
    يا
    1.05
    هاي
    1.04
    d
    1.00
    正
    0.99
    该
    0.98
    Activations Density 0.002%

    No Known Activations