© 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. 163633
    Prev
    Next
    INDEX
    Explanations

    handles complexity

    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
    '=>
    0.39
     एक्शन
    0.38
    chor
    0.38
    さて
    0.38
     येऊ
    0.37
     paneles
    0.37
    atth
    0.36
     disponible
    0.36
     tiende
    0.36
    <unused4>
    0.36
    POSITIVE LOGITS
     تب
    0.38
     방정식
    0.36
    心思
    0.36
     gosto
    0.36
     змі
    0.36
    Concurrent
    0.36
    本身
    0.35
     itself
    0.35
     wander
    0.34
     hunt
    0.34
    Activations Density 0.008%

    No Known Activations