© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165020
    Prev
    Next
    INDEX
    Explanations

    **Focus on highlighting specific arguments or details**

    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_31_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
     beautiful
    0.47
    淝
    0.44
     plen
    0.43
     schönen
    0.42
    Koordin
    0.41
     জাগ
    0.41
     corrective
    0.40
     wundersch
    0.40
     schöne
    0.39
     solves
    0.39
    POSITIVE LOGITS
     якобы
    0.40
     pretending
    0.39
     allegedly
    0.38
     pretended
    0.38
    輋
    0.37
     ostensibly
    0.37
     pretend
    0.36
    ጐ
    0.36
    本文
    0.35
     presumably
    0.35
    Activations Density 0.002%

    No Known Activations