© 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. 57428
    Prev
    Next
    INDEX
    Explanations

    to define or expire

    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
    PS
    0.70
    IM
    0.68
    V
    0.65
    PSD
    0.64
    L
    0.64
    SP
    0.63
    T
    0.63
    SDS
    0.62
    AP
    0.61
    AG
    0.61
    POSITIVE LOGITS
     malicious
    0.67
     negotiated
    0.66
     derailed
    0.66
     pursuant
    0.65
     negotiators
    0.65
     Kapol
    0.64
    :“
    0.61
     syscall
    0.60
     emblematic
    0.60
    ेंटिस
    0.60
    Activations Density 0.003%

    No Known Activations