© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214317
    Prev
    Next
    INDEX
    Explanations

    € symbol

    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_5_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
    1.57
    та
    1.06
     necessárias
    1.05
    )
    0.98
     beauté
    0.95
     vendita
    0.94
     próprias
    0.94
    쐞
    0.93
    şi
    0.92
    šenje
    0.92
    POSITIVE LOGITS
    d
    2.27
    h
    2.11
    s
    1.90
    p
    1.70
    د
    1.70
    g
    1.62
    in
    1.53
    ↵↵
    1.49
    c
    1.40
    m
    1.37
    Activations Density 0.000%

    No Known Activations