© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4224
    Prev
    Next
    INDEX
    Explanations

    service interface, mode, or class

    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_39_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
    Conver
    0.37
    NotDefined
    0.37
    -->'
    0.35
    subsec
    0.35
     Qg
    0.34
    lef
    0.33
    xffff
    0.33
     бюджет
    0.33
     горе
    0.33
    Subset
    0.32
    POSITIVE LOGITS
    箩
    0.42
    orted
    0.41
     तोला
    0.41
     realizes
    0.39
     lanes
    0.38
     আক্রমণের
    0.38
     jordan
    0.38
    pees
    0.38
    fowl
    0.38
    orms
    0.37
    Activations Density 0.018%

    No Known Activations