© 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. 49304
    Prev
    Next
    INDEX
    Explanations

    on Its, on a, on an

    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
     accompanied
    0.35
    沦
    0.32
    cepteur
    0.32
     fals
    0.31
     அதிகம்
    0.31
    હિ
    0.31
    ținut
    0.31
     ملاقات
    0.31
    erder
    0.30
    ")}}'
    0.30
    POSITIVE LOGITS
     ridge
    0.42
    នៅលើ
    0.39
    邙
    0.39
     モダン
    0.39
    Cit
    0.37
     drywall
    0.37
     vantage
    0.36
     ridges
    0.36
    促進
    0.36
     চিত্রক
    0.35
    Activations Density 0.000%

    No Known Activations