© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198973
    Prev
    Next
    INDEX
    Explanations

    sql update set column

    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_27_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
    rocessor
    0.37
    宁
    0.36
     "".
    0.36
    ensitivity
    0.35
     piety
    0.35
     sensibilité
    0.35
     Ning
    0.35
     указыва
    0.34
     ""
    0.34
     sensitivity
    0.32
    POSITIVE LOGITS
     yapılır
    0.42
    స్కీ
    0.37
     বিশ্র
    0.37
     ಭಾಗ
    0.35
    獃
    0.35
    elsen
    0.35
    ваны
    0.35
    牰
    0.35
    WHERE
    0.34
    мые
    0.34
    Activations Density 0.000%

    No Known Activations