© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7023
    Prev
    Next
    INDEX
    Explanations

    conversational interjections

    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
     صع
    0.33
    聋
    0.31
     adrenergic
    0.31
     setValue
    0.30
     proteolytic
    0.30
     findPlayer
    0.30
     जबरदस्त
    0.29
     मनोविज्ञान
    0.29
    ковы
    0.29
    讒
    0.28
    POSITIVE LOGITS
    Jurassic
    0.38
     Beige
    0.37
    apparently
    0.36
    Ghost
    0.35
    Ze
    0.35
     hipster
    0.35
     being
    0.34
    Hey
    0.34
    Netflix
    0.34
    Okay
    0.33
    Activations Density 0.139%

    No Known Activations