© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164415
    Prev
    Next
    INDEX
    Explanations

    chess pieces and notation

    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_13_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
     coulomb
    0.57
    ))+\
    0.55
    »),
    0.52
     অভিহিত
    0.52
    เชสเตอร์
    0.52
    候选
    0.51
     diskut
    0.51
    
    0.51
    »).
    0.50
     strontium
    0.50
    POSITIVE LOGITS
    IO
    0.63
    AR
    0.60
    IT
    0.58
    ich
    0.57
    N
    0.57
    ET
    0.56
    END
    0.55
    G
    0.54
    W
    0.53
    TR
    0.52
    Activations Density 0.000%

    No Known Activations