© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202811
    Prev
    Next
    INDEX
    Explanations

    Environmental impact

    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_12_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
    ta
    0.49
     }-
    0.48
     neuroscience
    0.45
    }-
    0.43
    \}-
    0.42
    }~
    0.42
     cycles
    0.42
     academia
    0.42
    ა
    0.41
     *
    0.41
    POSITIVE LOGITS
    ამაშ
    0.47
    인
    0.46
    ეტ
    0.45
    install
    0.44
     Server
    0.44
     fiel
    0.43
    раи
    0.43
    .',
    0.42
    ئین
    0.42
    瀕
    0.42
    Activations Density 0.001%

    No Known Activations