© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198731
    Prev
    Next
    INDEX
    Explanations

    short duration

    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_27_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
    гур
    0.46
     ប៉ុ
    0.42
    ériment
    0.42
    曠
    0.41
    delay
    0.41
     delaying
    0.40
     néanmoins
    0.40
     nevertheless
    0.39
    延
    0.39
    过程中
    0.39
    POSITIVE LOGITS
     quickly
    0.46
     already
    0.46
     Path
    0.41
     sooner
    0.40
     pendek
    0.38
     reco
    0.38
     short
    0.38
     soon
    0.38
     cepat
    0.38
     progress
    0.37
    Activations Density 0.028%

    No Known Activations