© 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. 8102
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

    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
     rehabilitate
    0.37
     tabi
    0.37
     lather
    0.37
     оюндары
    0.36
     Rah
    0.36
     밖에
    0.36
    ेंगू
    0.35
    宓
    0.35
     Explor
    0.35
    वारी
    0.35
    POSITIVE LOGITS
    侏
    0.40
    acidad
    0.38
     opportunity
    0.37
    opportunity
    0.35
    急
    0.35
    ripción
    0.35
    iprocal
    0.35
    ניין
    0.34
     ord
    0.33
    upam
    0.33
    Activations Density 0.099%

    No Known Activations