© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237537
    Prev
    Next
    INDEX
    Explanations

    crime, years, urban

    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_32_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
    🏾
    0.40
    abytes
    0.39
    eta
    0.36
     catered
    0.35
    phia
    0.35
    amides
    0.35
     味
    0.34
     lomb
    0.33
    copyWith
    0.33
     adolescentes
    0.33
    POSITIVE LOGITS
     dictum
    0.41
    nisse
    0.40
    冚
    0.39
     プ
    0.38
    +"|
    0.36
     punctatis
    0.36
     Prat
    0.36
     aspirants
    0.36
     Sauna
    0.35
     охра
    0.35
    Activations Density 0.013%

    No Known Activations