© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54375
    Prev
    Next
    INDEX
    Explanations

    urgency and limited-time offers

    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
     올라
    0.37
    DropDownList
    0.37
    churn
    0.35
    葙
    0.34
    勧
    0.34
     स्टार
    0.33
    棫
    0.33
     antimicrobial
    0.32
     trib
    0.32
     disinformation
    0.32
    POSITIVE LOGITS
    ceptors
    0.39
    โป
    0.39
     kostet
    0.38
    cted
    0.37
     Boring
    0.37
    琴
    0.37
    芥
    0.37
    anced
    0.37
    NEEDED
    0.36
     Digit
    0.36
    Activations Density 0.005%

    No Known Activations