© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150349
    Prev
    Next
    INDEX
    Explanations

    dust and cleaning

    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_18_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
     accede
    0.22
     handgun
    0.21
     equilibr
    0.21
    ोड
    0.20
     ܗ
    0.20
    出的
    0.19
     prohibit
    0.19
     mmHg
    0.19
    នឹង
    0.18
     해당
    0.18
    POSITIVE LOGITS
    禛
    0.19
    знав
    0.19
     വ്യാ
    0.18
     ricerca
    0.18
    azen
    0.18
    ค้น
    0.18
     структуру
    0.18
    Confident
    0.17
    ief
    0.17
    jani
    0.17
    Activations Density 0.004%

    No Known Activations