© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247091
    Prev
    Next
    INDEX
    Explanations

    Diamond Head

    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_40_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
     شعر
    0.43
     তর
    0.38
    urias
    0.37
     బ్రిటిషు
    0.37
     الشعر
    0.36
    罪
    0.36
     selenium
    0.36
    neas
    0.36
    nosť
    0.36
    Ὁ
    0.36
    POSITIVE LOGITS
    watering
    0.38
    closing
    0.37
    geno
    0.36
    terminate
    0.36
    Cell
    0.36
    acute
    0.35
     continuity
    0.34
     Bloomington
    0.34
     aperto
    0.34
    dipl
    0.34
    Activations Density 0.000%

    No Known Activations