© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40894
    Prev
    Next
    INDEX
    Explanations

    unravel secrets or plans

    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_11_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
    gal
    0.22
    ↵
    0.21
    ال
    0.20
    Chick
    0.20
    ilaian
    0.20
    kol
    0.20
     powied
    0.20
    0
    0.20
    Pumpkin
    0.19
    xs
    0.19
    POSITIVE LOGITS
    .}
    0.25
     tornando
    0.24
     IAAF
    0.24
    㞖
    0.24
     }.
    0.24
     GQ
    0.24
     Improving
    0.23
     .$
    0.23
     \&
    0.23
    ﯽ
    0.23
    Activations Density 0.011%

    No Known Activations