© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134300
    Prev
    Next
    INDEX
    Explanations

    PR and prove

    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_1_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
    </h2>
    1.38
    िंग
    1.26
    ة
    1.25
    ↵
    1.23
    ing
    1.14
    ЕВ
    1.14
    л
    1.12
    Գ
    1.12
    is
    1.09
    us
    1.09
    POSITIVE LOGITS
    ก
    1.07
     It
    0.94
    야
    0.92
     that
    0.91
    Tec
    0.91
     THAT
    0.89
    ched
    0.89
     whore
    0.89
    다면
    0.88
    x
    0.88
    Activations Density 0.000%

    No Known Activations