© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45150
    Prev
    Next
    INDEX
    Explanations

    job offer acceptance

    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_22_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
     attentions
    0.45
     तैनाती
    0.44
     maxit
    0.43
     المصفوفه
    0.42
     zelfs
    0.42
     Aufmerksamkeit
    0.41
    紓
    0.41
     ट्रू
    0.40
     camshaft
    0.39
    input
    0.39
    POSITIVE LOGITS
    查
    0.45
    Esp
    0.44
     بح
    0.43
    ின
    0.43
     Portman
    0.42
    GALL
    0.41
     tân
    0.39
    画
    0.39
    нено
    0.39
    BUR
    0.39
    Activations Density 0.002%

    No Known Activations