© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172367
    Prev
    Next
    INDEX
    Explanations

    video encoding pipelines

    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
     Exo
    0.43
    exit
    0.43
    exo
    0.43
     dialogo
    0.41
    ဋ
    0.38
    stake
    0.37
    usual
    0.36
     G
    0.36
    cross
    0.36
    iot
    0.35
    POSITIVE LOGITS
     entfernen
    0.42
    зме
    0.40
     verwij
    0.39
     нав
    0.39
    женности
    0.39
     redesignated
    0.38
     removals
    0.38
     removal
    0.38
     PROFITS
    0.38
     shi
    0.37
    Activations Density 0.003%

    No Known Activations