© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170942
    Prev
    Next
    INDEX
    Explanations

    delay

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ೀರಿ
    0.38
    wpt
    0.36
    stripos
    0.36
     recognising
    0.36
     révol
    0.35
     Verenig
    0.35
    榀
    0.35
    incott
    0.35
    堞
    0.35
     SwitchCompat
    0.33
    POSITIVE LOGITS
     delay
    2.56
     Delay
    2.44
    Delay
    2.42
    delay
    2.36
     delayed
    2.30
     delays
    2.25
     delaying
    2.19
     Delayed
    2.17
    Delayed
    2.09
    延迟
    2.08
    Activations Density 0.002%

    No Known Activations