© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4428
    Prev
    Next
    INDEX
    Explanations

    kotlin `fun`

    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
    inelli
    0.42
    nera
    0.39
    izoen
    0.39
    áneo
    0.38
    (_.
    0.38
    ipore
    0.38
    歿
    0.38
    𒂵
    0.37
    igene
    0.37
    elight
    0.37
    POSITIVE LOGITS
    fun
    0.47
     fun
    0.41
    enqueue
    0.39
     Fun
    0.39
    Fun
    0.39
     Regulations
    0.38
     Tail
    0.37
    sendCommand
    0.35
     активи
    0.35
    kých
    0.35
    Activations Density 0.010%

    No Known Activations