© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29343
    Prev
    Next
    INDEX
    Explanations

    disclaimer

    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_10_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
    يل
    0.44
    \
    0.37
    ség
    0.35
    ير
    0.33
    in
    0.33
    ischen
    0.33
    ية
    0.33
    ్రో
    0.33
    z
    0.32
    siniz
    0.32
    POSITIVE LOGITS
     testicular
    0.38
     refe
    0.36
     testis
    0.34
     penj
    0.33
     probleml
    0.33
     timer
    0.32
     recalc
    0.32
    oa
    0.32
     neoprene
    0.32
     senescence
    0.31
    Activations Density 0.101%

    No Known Activations