© 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. 159169
    Prev
    Next
    INDEX
    Explanations

    offering help

    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
    HasFieldError
    0.42
     मीडियम
    0.40
     Herm
    0.38
     världen
    0.38
    Ỳ
    0.37
    HT
    0.35
     ба
    0.35
    ậc
    0.35
     peral
    0.35
    HAS
    0.35
    POSITIVE LOGITS
     تمت
    0.40
     professionalism
    0.38
     ape
    0.38
    crew
    0.37
    経験
    0.37
    ttl
    0.37
    assignment
    0.37
    otro
    0.37
     सवारी
    0.36
    apest
    0.36
    Activations Density 0.002%

    No Known Activations