© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2088
    Prev
    Next
    INDEX
    Explanations

    unexpected uses of

    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
    Ϩ
    0.39
     JOHNSON
    0.38
    hower
    0.37
    CCCc
    0.36
    Specificity
    0.36
    Inicio
    0.36
    Ӏ
    0.36
    퐫
    0.35
    頴
    0.35
    Swap
    0.35
    POSITIVE LOGITS
     pardon
    0.45
     broken
    0.38
     camera
    0.37
     unknow
    0.37
     breakage
    0.37
     camer
    0.36
     akad
    0.36
     assail
    0.36
     photographer
    0.36
     abroad
    0.35
    Activations Density 0.276%

    No Known Activations