© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154710
    Prev
    Next
    INDEX
    Explanations

    which/who/what

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     मद
    0.40
    †
    0.37
     maiden
    0.36
    াৎ
    0.36
    ‌پ
    0.35
     lc
    0.35
    
    0.35
     adam
    0.35
    
    0.35
     ell
    0.34
    POSITIVE LOGITS
    which
    0.84
     which
    0.69
    go
    0.67
    controller
    0.63
    GO
    0.63
     Which
    0.63
    Which
    0.60
     которая
    0.59
     laquelle
    0.59
     która
    0.58
    Activations Density 0.000%

    No Known Activations