© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24571
    Prev
    Next
    INDEX
    Explanations

    cars

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     maz
    0.66
     lex
    0.66
     kia
    0.64
    Maz
    0.64
     Maz
    0.59
     vol
    0.56
    Kia
    0.56
    丰
    0.56
     LEX
    0.55
     Genesis
    0.54
    POSITIVE LOGITS
    CSV
    0.45
     CSV
    0.44
    эг
    0.41
    വയ
    0.41
    nec
    0.41
    ühle
    0.39
    csv
    0.37
     csv
    0.37
    ندی
    0.37
    uhl
    0.36
    Activations Density 0.013%

    No Known Activations