© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101152
    Prev
    Next
    INDEX
    Explanations

    orchestral music, orchestration, orchestrate

    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_14_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
     guitars
    0.67
     torus
    0.62
     trombone
    0.61
     reals
    0.60
     mourn
    0.59
     spindles
    0.59
     cozinha
    0.59
    凃
    0.59
     subspaces
    0.58
     barges
    0.58
    POSITIVE LOGITS
    or
    0.59
    isca
    0.56
    au
    0.55
     (
    0.55
    ora
    0.55
    ization
    0.54
    тации
    0.54
    ica
    0.54
    j
    0.52
    en
    0.50
    Activations Density 0.000%

    No Known Activations