© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31852
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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_31_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
     INTERRUPTION
    0.37
    lö
    0.35
     /.
    0.35
     Carlos
    0.34
     ilma
    0.34
    cardo
    0.34
     Jacobsen
    0.34
     Tags
    0.33
     Plug
    0.33
     Dug
    0.33
    POSITIVE LOGITS
     싶
    0.39
    砊
    0.37
     conviene
    0.37
    䚲
    0.36
    更
    0.36
     deff
    0.36
    aunque
    0.35
    Camel
    0.35
    าราง
    0.35
     equivale
    0.35
    Activations Density 0.000%

    No Known Activations