© 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. 151087
    Prev
    Next
    INDEX
    Explanations

    acronyms and codes

    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
     પ
    0.50
    prav
    0.50
     Phoebe
    0.49
     L
    0.45
     Baru
    0.45
     Penc
    0.44
     Pia
    0.44
     Punta
    0.44
     الل
    0.43
    pura
    0.43
    POSITIVE LOGITS
    s
    1.32
    ی
    0.83
    ের
    0.81
    ים
    0.77
    a
    0.77
    ों
    0.70
    ओं
    0.67
    sby
    0.65
    ς
    0.63
    ਆਂ
    0.61
    Activations Density 0.000%

    No Known Activations