© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132622
    Prev
    Next
    INDEX
    Explanations

    WebSocket

    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_6_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
    ות
    1.27
    UG
    1.27
    מ
    1.27
    ב
    1.23
    IM
    1.13
     has
    1.09
    ↵↵
    1.05
     and
    1.04
    ED
    1.03
     מ
    1.03
    POSITIVE LOGITS
    are
    1.33
    もら
    1.12
    ai
    1.06
    rives
    1.05
    orin
    1.04
    r
    1.04
    weiß
    1.03
    em
    1.00
    rages
    1.00
    esting
    0.99
    Activations Density 0.001%

    No Known Activations