© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4672
    Prev
    Next
    INDEX
    Explanations

    named entities and numbers

    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_39_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
     Bist
    0.37
    萺
    0.36
    涳
    0.36
     bho
    0.36
     парази
    0.35
     Nonlinear
    0.35
     returnValue
    0.34
    λάβ
    0.34
     прос
    0.33
     jaaye
    0.33
    POSITIVE LOGITS
    messaging
    0.37
     publicit
    0.37
     paździer
    0.36
    |}\
    0.35
     spokesman
    0.35
    Stra
    0.35
    历史上
    0.35
    ión
    0.34
    រប
    0.34
     nummer
    0.34
    Activations Density 0.012%

    No Known Activations