© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65683
    Prev
    Next
    INDEX
    Explanations

    return to

    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_41_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
     Returns
    0.43
    Returns
    0.42
     return
    0.41
    Retour
    0.40
    ^{[\
    0.39
    чном
    0.39
     returned
    0.38
     ritorno
    0.37
    Returning
    0.36
    },}
    0.36
    POSITIVE LOGITS
     toa
    0.50
     To
    0.48
     домой
    0.48
     home
    0.47
     whence
    0.47
    to
    0.46
    To
    0.45
     إلى
    0.44
    ToBase
    0.43
    ceiver
    0.41
    Activations Density 0.003%

    No Known Activations