© 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. 39493
    Prev
    Next
    INDEX
    Explanations

    manche / manchmal / kann / andere

    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
     ទ
    0.64
    ğmen
    0.55
    DanhMucSP
    0.55
     ಸ್ವ
    0.55
    }$).
    0.55
     établir
    0.55
     कै
    0.54
    んにちは
    0.53
     impuestos
    0.52
     επισ
    0.52
    POSITIVE LOGITS
     cleaner
    0.54
     cubo
    0.54
    (
    0.54
     police
    0.53
     Nashville
    0.53
     versatile
    0.52
     s
    0.51
     Metro
    0.51
     officer
    0.51
     metro
    0.50
    Activations Density 0.000%

    No Known Activations