© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246597
    Prev
    Next
    INDEX
    Explanations

    delete or clearInterval

    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_40_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
    órios
    0.38
    “[
    0.37
     χει
    0.36
    rij
    0.35
    グラン
    0.35
     جای
    0.34
     compacto
    0.34
     சது
    0.34
    寓
    0.33
     “[
    0.33
    POSITIVE LOGITS
    FG
    0.44
    항
    0.44
    Docs
    0.41
     হানাদার
    0.40
    陉
    0.39
    ahuan
    0.39
    ங்கள
    0.38
    вшие
    0.38
    मिटेड
    0.38
     albi
    0.38
    Activations Density 0.000%

    No Known Activations