© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150502
    Prev
    Next
    INDEX
    Explanations

    K

    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_60_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
    s
    0.43
    f
    0.43
     civilized
    0.40
     committing
    0.40
     conventional
    0.40
     converting
    0.39
     adding
    0.39
     configured
    0.38
     discharges
    0.38
     uploads
    0.38
    POSITIVE LOGITS
     Kosten
    0.50
    اک
    0.49
    inko
    0.49
     Kuro
    0.46
    𝗞
    0.46
     Corolle
    0.45
    karte
    0.44
    picode
    0.44
     Roxy
    0.44
    iguiente
    0.43
    Activations Density 0.001%

    No Known Activations