© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175915
    Prev
    Next
    INDEX
    Explanations

    Pearl Harbor

    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_20_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
     Gör
    0.42
    ăz
    0.41
    opia
    0.41
    vapor
    0.41
     本当
    0.41
    嘔
    0.39
    一组
    0.39
    ë
    0.39
    以前
    0.39
    expansive
    0.39
    POSITIVE LOGITS
     initializes
    0.45
    COMDAT
    0.45
     caes
    0.45
     atan
    0.42
     demais
    0.42
     patrolling
    0.41
     động
    0.41
     attaques
    0.40
     shrines
    0.40
    فاف
    0.40
    Activations Density 0.001%

    No Known Activations