© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130398
    Prev
    Next
    INDEX
    Explanations

    National

    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_50_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
    Carter
    0.42
     σκο
    0.39
     Carter
    0.38
    rob
    0.38
    nesset
    0.38
    磷
    0.38
    jete
    0.37
    crib
    0.37
    낀
    0.37
    èn
    0.36
    POSITIVE LOGITS
     Pax
    0.46
    Pax
    0.44
     pax
    0.43
     Paw
    0.41
     namespace
    0.40
     PAX
    0.40
     point
    0.39
     Point
    0.39
    IDI
    0.38
     Jno
    0.38
    Activations Density 0.003%

    No Known Activations