© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159494
    Prev
    Next
    INDEX
    Explanations

    argyle socks

    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
    '
    1.54
    ’
    1.29
    ER
    1.24
     for
    1.13
    '";
    1.13
    UR
    1.09
    ी
    1.09
    EL
    1.08
    OM
    1.06
    H
    1.06
    POSITIVE LOGITS
    };
    1.03
     in
    1.02
    in
    1.01
     في
    0.80
    德
    0.79
    اد
    0.75
    。",
    0.71
    在
    0.71
    も
    0.71
    ও
    0.71
    Activations Density 0.000%

    No Known Activations