© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134669
    Prev
    Next
    INDEX
    Explanations

    package.json dependencies

    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
     CryptoJS
    0.43
     Fórmula
    0.41
     Employment
    0.39
     !==
    0.38
     epidermal
    0.38
    掂
    0.38
    唦
    0.38
    开发者
    0.37
     obbl
    0.37
    恚
    0.37
    POSITIVE LOGITS
     publish
    0.41
     publicados
    0.40
     preview
    0.38
    Everyone
    0.37
    preview
    0.36
    IGroup
    0.36
    fs
    0.36
    Album
    0.36
    pdbonly
    0.36
    Exc
    0.35
    Activations Density 0.000%

    No Known Activations