© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176252
    Prev
    Next
    INDEX
    Explanations

    scenes and time indicators

    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_20_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
    sem
    0.41
    Semester
    0.37
    agle
    0.36
    ϕ
    0.36
    시스템
    0.36
     واس
    0.36
    Philip
    0.35
    њем
    0.35
    zel
    0.35
     Tuhan
    0.35
    POSITIVE LOGITS
    萎
    0.39
     residencial
    0.39
     अधिका
    0.39
     riun
    0.38
     dividing
    0.38
     हेतु
    0.37
     masts
    0.37
     mă
    0.37
    国外
    0.37
     তাছাড়া
    0.37
    Activations Density 0.000%

    No Known Activations