© 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. 7418
    Prev
    Next
    INDEX
    Explanations

    Where-Object condition

    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
    hely
    0.39
    lfloor
    0.39
     fa
    0.38
     flag
    0.37
    Murphy
    0.37
     managers
    0.37
    MANAG
    0.36
    偐
    0.36
    舧
    0.36
    გი
    0.36
    POSITIVE LOGITS
     Object
    0.42
    Object
    0.39
    Jacobi
    0.38
    étrica
    0.37
    ttino
    0.37
    ेयर
    0.36
     Chunk
    0.36
     त्व
    0.36
     differentiable
    0.36
    CHUNK
    0.36
    Activations Density 0.001%

    No Known Activations