© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11444
    Prev
    Next
    INDEX
    Explanations

    data manipulation methods

    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_40_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
     পুষ
    0.39
     privat
    0.39
     プ
    0.38
     তখনও
    0.37
    ﭘ
    0.36
    κος
    0.36
     টে
    0.35
    ..--
    0.35
     privato
    0.35
     beteil
    0.35
    POSITIVE LOGITS
     stopwords
    0.38
    icheskij
    0.38
    emp
    0.38
    \|,
    0.37
     അവ
    0.37
     scopes
    0.37
     mát
    0.37
     scooters
    0.36
     ô
    0.36
    createStatement
    0.36
    Activations Density 0.003%

    No Known Activations