© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211082
    Prev
    Next
    INDEX
    Explanations

    security and encryption

    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_19_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
     Polar
    0.47
     woning
    0.47
    住
    0.47
     culoare
    0.46
     cintura
    0.46
     Centro
    0.46
     Centre
    0.46
     dividir
    0.44
    祐
    0.44
    今年の
    0.44
    POSITIVE LOGITS
    fs
    0.55
    ests
    0.50
    leness
    0.48
    hardness
    0.47
    EXEC
    0.46
    ist
    0.45
    log
    0.45
    UR
    0.45
    anish
    0.44
    bler
    0.44
    Activations Density 0.001%

    No Known Activations