© 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. 137184
    Prev
    Next
    INDEX
    Explanations

    let's dive in

    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
    un
    0.67
    -
    0.59
    ot
    0.58
    as
    0.57
    ad
    0.55
         
    0.55
    ↵
    0.54
    ut
    0.54
    hi
    0.54
    ান
    0.54
    POSITIVE LOGITS
    OGND
    0.60
     giusta
    0.59
    вары
    0.58
    σεις
    0.56
    ودة
    0.56
     Hoàng
    0.56
     $("<
    0.56
    োদয়
    0.56
    瓠
    0.56
    लोड
    0.55
    Activations Density 0.001%

    No Known Activations