© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41811
    Prev
    Next
    INDEX
    Explanations

    Paul Allen, Paul Newman, Henri names

    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_3_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
    ğ
    0.63
    νων
    0.63
    ல்
    0.62
    ğın
    0.61
     نہيں
    0.61
     Lúc
    0.59
    ﻪ
    0.59
    rfloor
    0.59
    implies
    0.58
    င်
    0.58
    POSITIVE LOGITS
     in
    0.93
    '
    0.89
     در
    0.80
    在
    0.79
    .
    0.74
    )
    0.72
    ใน
    0.68
     synthes
    0.66
     of
    0.63
    ).
    0.61
    Activations Density 0.001%

    No Known Activations