© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241897
    Prev
    Next
    INDEX
    Explanations

    data generation in code

    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
     según
    0.38
     ao
    0.36
     au
    0.35
     días
    0.35
     giorno
    0.35
    资
    0.35
    CNR
    0.35
     defraud
    0.34
     znal
    0.34
     дня
    0.34
    POSITIVE LOGITS
     Anticip
    0.37
     형태
    0.36
    惇
    0.34
    форма
    0.34
     anticipated
    0.34
     plurality
    0.34
     anticipating
    0.34
    یدن
    0.33
    öö
    0.33
    Premi
    0.33
    Activations Density 0.001%

    No Known Activations