© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54446
    Prev
    Next
    INDEX
    Explanations

    hor

    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_55_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
     short
    3.58
    short
    3.25
     Short
    3.13
    Short
    3.09
    短
    3.08
     корот
    3.00
     SHORT
    2.97
     kısa
    2.70
    SHORT
    2.66
     短
    2.55
    POSITIVE LOGITS
    forRoot
    0.36
     antipode
    0.34
    чу
    0.34
     سعید
    0.33
    änglich
    0.33
    နယ်
    0.32
    ERRORTYPE
    0.32
    iew
    0.31
    യി
    0.31
    ücklich
    0.31
    Activations Density 0.006%

    No Known Activations