© 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. 243014
    Prev
    Next
    INDEX
    Explanations

    code blocks and technical contexts

    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
     Pá
    0.43
     διαφορε
    0.40
     Dug
    0.40
     different
    0.39
     logika
    0.38
     diferentes
    0.38
     farklı
    0.37
    缚
    0.37
     dug
    0.37
    ώ
    0.37
    POSITIVE LOGITS
    荧
    0.43
    mbH
    0.41
    otype
    0.40
     சு
    0.39
     შემთ
    0.39
     terminals
    0.39
    ıya
    0.38
    ッテ
    0.38
    antial
    0.38
    จำเป็น
    0.37
    Activations Density 0.000%

    No Known Activations