© 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. 134919
    Prev
    Next
    INDEX
    Explanations

    I'm not perfect

    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
     profesión
    0.51
     člove
    0.45
     profession
    0.42
     профессии
    0.42
     चुंबकीय
    0.41
    衢
    0.39
    職業
    0.38
     mennes
    0.38
     인간
    0.38
     prepared
    0.38
    POSITIVE LOGITS
     Holds
    0.36
     holds
    0.36
    ී
    0.35
    baby
    0.35
    session
    0.35
    Holds
    0.34
    dagger
    0.34
     بست
    0.34
    contains
    0.34
    observer
    0.34
    Activations Density 0.004%

    No Known Activations