© 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. 246207
    Prev
    Next
    INDEX
    Explanations

    refer to instructions or documentation

    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
    乘以
    0.41
    getBy
    0.39
     उनसे
    0.39
    朝着
    0.37
    㞰
    0.37
     অন্যের
    0.36
    他の
    0.35
     papal
    0.35
     ESPN
    0.35
     universidad
    0.35
    POSITIVE LOGITS
    ୍
    0.40
    ónde
    0.37
     gratis
    0.36
    )(((
    0.36
     ওঠ
    0.35
    呑
    0.34
    ivate
    0.34
    ಲ್ಲು
    0.34
    ondo
    0.34
    Native
    0.34
    Activations Density 0.113%

    No Known Activations