© 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. 31670
    Prev
    Next
    INDEX
    Explanations

    ingredients listings

    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
    fishing
    0.38
     fud
    0.37
     जल्
    0.35
    ណ
    0.35
     സാ
    0.34
    彡
    0.34
    CHINA
    0.33
    ເ
    0.33
    ナム
    0.33
     fishing
    0.33
    POSITIVE LOGITS
     kau
    0.34
     पढ़िए
    0.34
     Originally
    0.34
     modal
    0.32
     Wiel
    0.32
     XI
    0.32
     originally
    0.31
     hiz
    0.31
     Eust
    0.31
     Nort
    0.31
    Activations Density 0.014%

    No Known Activations