© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167551
    Prev
    Next
    INDEX
    Explanations

    json parsing/encoding in Go/Dart

    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_34_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
     pasada
    0.39
     भुव
    0.38
     baw
    0.37
    Notes
    0.37
     Written
    0.35
    $"
    0.35
     khóa
    0.35
    गंगा
    0.35
     trasmissione
    0.34
     lock
    0.34
    POSITIVE LOGITS
     Powerful
    0.44
    entgen
    0.42
    kiy
    0.40
     Kue
    0.39
    powerful
    0.38
    rectionType
    0.38
     powerful
    0.37
    ലിം
    0.37
    calling
    0.36
    ｜
    0.36
    Activations Density 0.000%

    No Known Activations