© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18402
    Prev
    Next
    INDEX
    Explanations

    math and code separators

    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_15_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
    ci
    0.15
    ebox
    0.15
    ford
    0.15
    ens
    0.14
    ffes
    0.14
    chus
    0.14
    ř
    0.14
    cí
    0.14
    cke
    0.14
    ers
    0.14
    POSITIVE LOGITS
     categorically
    0.15
    راتيج
    0.15
    nomes
    0.15
     labelling
    0.14
     وان
    0.14
    ഹാ
    0.14
     verdict
    0.14
     DIRECTION
    0.14
     cambiando
    0.14
    蜿
    0.14
    Activations Density 0.155%

    No Known Activations