© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66401
    Prev
    Next
    INDEX
    Explanations

    word parts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
     annuities
    0.38
    یب
    0.38
     Shub
    0.38
    শু
    0.36
     ഇമാ
    0.36
    zut
    0.36
    可以看出
    0.36
    <0x06>
    0.35
    nj
    0.35
    䣵
    0.35
    POSITIVE LOGITS
    ره
    0.54
    re
    0.53
    res
    0.53
    رة
    0.48
    reh
    0.48
    рес
    0.47
    RES
    0.46
    ре
    0.44
    me
    0.44
    ρει
    0.43
    Activations Density 0.003%

    No Known Activations