© 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. 57683
    Prev
    Next
    INDEX
    Explanations

    non-negotiable

    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
    ун
    0.71
    ведите
    0.68
     Нет
    0.67
    проце
    0.66
    ுண்டு
    0.64
     Най
    0.64
    ètent
    0.63
    с
    0.63
    䟧
    0.63
    Нет
    0.62
    POSITIVE LOGITS
     was
    0.84
    0.79
     a
    0.66
     .
    0.64
     ,
    0.63
     :
    0.63
     MIS
    0.61
    H
    0.61
     ]
    0.59
    i
    0.59
    Activations Density 0.001%

    No Known Activations