© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169280
    Prev
    Next
    INDEX
    Explanations

    without

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     meeting
    0.68
     Meeting
    0.66
    Meeting
    0.64
    meeting
    0.57
     MEETING
    0.55
     t
    0.47
     मीटिंग
    0.47
     passing
    0.42
     Passing
    0.42
     remaining
    0.40
    POSITIVE LOGITS
     και
    0.64
     और
    0.64
     и
    0.62
     ಮತ್ತು
    0.60
    और
    0.60
    ແລະ
    0.60
    และ
    0.59
     và
    0.58
     এবং
    0.57
     आणि
    0.57
    Activations Density 0.002%

    No Known Activations