© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218964
    Prev
    Next
    INDEX
    Explanations

    loop index `i`

    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
    ="|
    0.38
     Troy
    0.37
    ඥ
    0.37
     संवाददाता
    0.36
    angleright
    0.36
     मसा
    0.35
     Regeln
    0.35
     Schluss
    0.35
    rossovers
    0.35
     Fey
    0.34
    POSITIVE LOGITS
     wastes
    0.38
    俯
    0.37
    Went
    0.36
     Reflection
    0.35
    شت
    0.35
    烘
    0.34
     അവിടെ
    0.34
    Ки
    0.34
    হইয়া
    0.34
    respectively
    0.33
    Activations Density 0.001%

    No Known Activations