© 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. 19177
    Prev
    Next
    INDEX
    Explanations

    STAR Method

    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
     UHF
    0.23
     desigual
    0.22
    ፩
    0.20
     Compressed
    0.20
     ballots
    0.20
     கன
    0.20
    [-
    0.20
    Due
    0.20
     byproduct
    0.19
     Trag
    0.19
    POSITIVE LOGITS
    يد
    0.26
    id
    0.24
     अदानी
    0.24
     описы
    0.24
    炡
    0.24
    NA
    0.23
     describe
    0.23
     describir
    0.23
     რომლებიც
    0.23
     ܗ
    0.22
    Activations Density 0.003%

    No Known Activations