© 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. 120179
    Prev
    Next
    INDEX
    Explanations

    Your email

    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
    ائق
    0.43
     चाइल्ड
    0.40
    ມັນ
    0.40
     primarySwatch
    0.39
     শিশু
    0.39
     않는
    0.38
    UVWXYZ
    0.38
    丵
    0.38
     শিশুদের
    0.37
    icult
    0.37
    POSITIVE LOGITS
     Austria
    0.43
    وە
    0.42
    ського
    0.41
     Amsterdam
    0.40
     Ottawa
    0.39
     networking
    0.39
     Switzerland
    0.38
     Austrian
    0.38
     gene
    0.38
     Swiss
    0.38
    Activations Density 0.005%

    No Known Activations