© 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. 194292
    Prev
    Next
    INDEX
    Explanations

    any group or both sides

    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
    ceği
    0.37
    commonByteArray
    0.37
     mostly
    0.35
     verwij
    0.34
    ໌
    0.34
    boxylate
    0.34
    轸
    0.34
     perceiving
    0.34
    getObject
    0.33
    忤
    0.33
    POSITIVE LOGITS
     द
    0.42
    LANG
    0.37
    民族
    0.35
    ீர்
    0.34
    畐
    0.34
     Equivalent
    0.34
     Oculus
    0.34
     Expressions
    0.33
     EQU
    0.33
     equivalent
    0.33
    Activations Density 0.052%

    No Known Activations