© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6012
    Prev
    Next
    INDEX
    Explanations

    text formatting and lists

    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_39_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
     funcionario
    0.38
     Secretario
    0.37
     fud
    0.37
     Kommission
    0.36
     Fakult
    0.36
    ப்பி
    0.35
    鶉
    0.35
    //!
    0.33
     Возможно
    0.33
    ంగళ
    0.33
    POSITIVE LOGITS
     bosses
    0.44
     Classic
    0.39
    Simon
    0.38
    조
    0.38
    figures
    0.37
    rizes
    0.37
    Gw
    0.37
    Claire
    0.37
    냅
    0.36
     outpatient
    0.36
    Activations Density 0.008%

    No Known Activations