© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125808
    Prev
    Next
    INDEX
    Explanations

    constructor, interval, alpha

    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_37_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
     Dec
    0.40
     May
    0.38
    ElementException
    0.37
    접
    0.37
     Macron
    0.37
     Convey
    0.36
     май
    0.35
     vor
    0.35
     Inf
    0.35
     Construct
    0.35
    POSITIVE LOGITS
     фрон
    0.40
    邀请
    0.39
    ণাস্ত্র
    0.39
    龛
    0.38
    шают
    0.38
    iconductor
    0.37
     electrification
    0.37
    infiltration
    0.37
     chieftain
    0.37
    招标
    0.36
    Activations Density 0.001%

    No Known Activations