© 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
    2. Gemma-3-27B-IT
    3. 6-GEMMASCOPE-2-TRANSCODER-262K
    4. 132539
    Prev
    Next
    INDEX
    Explanations

    exit, make, app, chat, pear, submissions, localhost

    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_6_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
    ed
    1.16
    4
    1.09
    ay
    1.09
    د
    1.08
    י
    1.07
     were
    1.06
    ために
    1.04
    ي
    1.03
    al
    1.02
     is
    1.02
    POSITIVE LOGITS
    к
    0.87
    ств
    0.79
    RA
    0.77
    Breakpoint
    0.77
    Tooltip
    0.75
     efectivamente
    0.75
    SERT
    0.74
     impresa
    0.73
    ResponseEntity
    0.73
    Simulator
    0.71
    Activations Density 0.014%

    No Known Activations