© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 157943
    Prev
    Next
    INDEX
    Explanations

    company names

    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
     Ll
    0.46
     LL
    0.42
     ll
    0.41
    LL
    0.41
     bitte
    0.39
     пожалуйста
    0.37
    ശ്
    0.37
    ♌
    0.37
    LLS
    0.36
     LLC
    0.36
    POSITIVE LOGITS
    ORS
    0.40
    min
    0.39
    iteta
    0.39
    ahin
    0.39
     Hyp
    0.38
     hypergeometric
    0.38
     Hy
    0.38
     prist
    0.38
     precipitated
    0.38
    tailed
    0.36
    Activations Density 0.001%

    No Known Activations