© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151147
    Prev
    Next
    INDEX
    Explanations

    qu

    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_60_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
     saying
    0.73
    说
    0.54
     Say
    0.52
     say
    0.51
     Saying
    0.47
     dizendo
    0.47
    Say
    0.45
     diciendo
    0.45
    say
    0.44
    說
    0.43
    POSITIVE LOGITS
    sh
    0.46
    のが
    0.45
    のは
    0.45
    名
    0.44
    combo
    0.44
    명
    0.41
    de
    0.41
    max
    0.41
     ап
    0.40
    úc
    0.39
    Activations Density 0.000%

    No Known Activations