© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 44163
    Prev
    Next
    INDEX
    Explanations

    guitar tablature or tabs

    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_13_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
    >
    0.60
    ;
    0.49
     Astronomical
    0.46
     descrito
    0.45
    இ
    0.45
     equiv
    0.44
     ..
    0.43
    >∕</
    0.43
     Corner
    0.42
     lequel
    0.41
    POSITIVE LOGITS
     confirms
    0.48
     allows
    0.48
     උප
    0.47
    උ
    0.46
     enables
    0.45
     powodu
    0.44
    ◈
    0.44
     sljede
    0.44
    UTO
    0.44
     nasce
    0.44
    Activations Density 0.000%

    No Known Activations