© 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. 201270
    Prev
    Next
    INDEX
    Explanations

    clinical laboratory, nutrition, neurosciences, practice

    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
     squid
    0.42
     Quantity
    0.38
     once
    0.37
    久
    0.37
    海南
    0.37
     Match
    0.36
     Численность
    0.36
    Kin
    0.36
    crocodile
    0.35
     counting
    0.35
    POSITIVE LOGITS
     मेड
    0.38
    hörigen
    0.37
    ⬇
    0.37
     Edmond
    0.37
     du
    0.36
     ergonomic
    0.36
     studs
    0.36
     Nxf
    0.35
    🄴
    0.35
    Centers
    0.35
    Activations Density 0.001%

    No Known Activations