© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140805
    Prev
    Next
    INDEX
    Explanations

    guitar sound to MIDI

    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_12_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
     Neurology
    0.53
    ʬ
    0.51
     backpacks
    0.50
    suitcase
    0.49
     suitcases
    0.48
     Dermatology
    0.47
     neurologist
    0.47
     \<
    0.46
    Pharmacy
    0.46
     Pharmacol
    0.46
    POSITIVE LOGITS
     o
    0.59
    ו
    0.58
     о
    0.57
    ோ
    0.52
    o
    0.52
    jän
    0.52
    수가
    0.51
    ു
    0.50
    el
    0.49
    东西
    0.49
    Activations Density 0.000%

    No Known Activations