© 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
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233772
    Prev
    Next
    INDEX
    Explanations

    Windows 10 versions

    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_46_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
     উই
    0.41
    qar
    0.39
    ешь
    0.36
     élus
    0.35
    伈
    0.35
    ურ
    0.35
     centrifuged
    0.35
     exempl
    0.34
     अली
    0.34
    UseDebug
    0.33
    POSITIVE LOGITS
     الجرس
    0.37
    inverse
    0.35
    icolor
    0.35
    욜
    0.35
     wants
    0.34
    nhof
    0.34
    VAC
    0.34
    >
    0.34
     Anspr
    0.34
    spring
    0.33
    Activations Density 0.001%

    No Known Activations