© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15342
    Prev
    Next
    INDEX
    Explanations

    QuantConnect powershell from system

    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
    Int
    0.40
    toMatch
    0.37
     Cm
    0.37
    Cm
    0.37
    S
    0.35
     Mn
    0.35
     грудня
    0.34
     fully
    0.34
    intrusion
    0.33
     Int
    0.33
    POSITIVE LOGITS
     clove
    0.44
    एफसी
    0.43
    moil
    0.40
    Ruf
    0.39
    FFER
    0.39
    崠
    0.39
     Synchronization
    0.38
    ujos
    0.38
    ajul
    0.38
     Szeged
    0.38
    Activations Density 0.067%

    No Known Activations