© 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. 227832
    Prev
    Next
    INDEX
    Explanations

    clears throat

    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
    1.19
    atation
    1.01
    in
    0.98
    بس
    0.95
    )
    0.92
    im
    0.90
    9
    0.87
    нили
    0.86
     αλλά
    0.86
    llä
    0.85
    POSITIVE LOGITS
    т
    1.48
    н
    1.13
    ਰ
    1.03
    ান
    0.97
    ET
    0.97
    ي
    0.97
    ir
    0.97
    ж
    0.93
    а
    0.92
    м
    0.91
    Activations Density 0.000%

    No Known Activations