© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61683
    Prev
    Next
    INDEX
    Explanations

    command, communication, systems, protocols

    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_11_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
     $)$.
    0.50
     ).
    0.49
    )،
    0.48
    ’-
    0.48
    </h2>
    0.47
    )").
    0.47
    ’).
    0.47
    </i>
    0.45
    ?).
    0.45
    яза
    0.43
    POSITIVE LOGITS
    ف
    0.60
    リュ
    0.59
    h
    0.54
    漓
    0.54
    デ
    0.53
    ሩ
    0.52
    逶
    0.52
     entier
    0.52
    シ
    0.52
    ⴼ
    0.51
    Activations Density 0.098%

    No Known Activations