© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23489
    Prev
    Next
    INDEX
    Explanations

    word endings

    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_56_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
    Single
    0.70
    单
    0.66
     Single
    0.65
     single
    0.64
    單
    0.62
    single
    0.61
     단
    0.59
     SINGLE
    0.55
     单
    0.55
     सिंगल
    0.53
    POSITIVE LOGITS
    iendo
    0.33
    cling
    0.31
    chid
    0.30
     ting
    0.29
     imponer
    0.29
    ader
    0.29
    itations
    0.29
    ningar
    0.29
    ivative
    0.29
     estar
    0.29
    Activations Density 0.000%

    No Known Activations