© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59984
    Prev
    Next
    INDEX
    Explanations

    model starts response

    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_59_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
    '=>'','
    0.47
    makarna
    0.43
    should
    0.43
    ,"@
    0.43
    ounid
    0.42
     (,
    0.42
    melidir
    0.41
    ','.
    0.40
     “”
    0.40
    ')['
    0.39
    POSITIVE LOGITS
    Ш
    0.43
     correct
    0.37
    Param
    0.36
    Ober
    0.36
    Sz
    0.36
    Sistema
    0.36
     find
    0.35
     initiatives
    0.35
     who
    0.34
     শহর
    0.34
    Activations Density 0.009%

    No Known Activations