© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246383
    Prev
    Next
    INDEX
    Explanations

    integer data structure node

    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
     LU
    0.44
    associ
    0.41
    ovac
    0.40
    月
    0.39
    LU
    0.39
     associ
    0.39
    ਖ਼
    0.38
     dijadikan
    0.38
    밝
    0.38
     Kannada
    0.37
    POSITIVE LOGITS
    ترم
    0.39
     பாவ
    0.38
    щением
    0.37
     anillo
    0.37
    DISABLED
    0.36
    IEE
    0.35
    zus
    0.35
    impul
    0.34
    WithMessage
    0.34
    ">)</
    0.34
    Activations Density 0.001%

    No Known Activations