© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59793
    Prev
    Next
    INDEX
    Explanations

    permissions, ownership, root

    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
    E
    0.59
    organisme
    0.56
    Lorsque
    0.55
    م
    0.55
    ח
    0.54
    Notes
    0.54
    soluble
    0.53
    C
    0.53
    on
    0.52
    SLE
    0.52
    POSITIVE LOGITS
    यन
    0.55
     phonon
    0.54
    
    0.54
    నీ
    0.52
    琕
    0.52
    ьера
    0.48
    órz
    0.48
    cityName
    0.48
    ियन
    0.48
    ividad
    0.48
    Activations Density 0.072%

    No Known Activations