© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 208281
    Prev
    Next
    INDEX
    Explanations

    section numbering and mathematical equations

    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_19_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
     livery
    0.14
     Credits
    0.14
     lighter
    0.14
     F
    0.13
     bow
    0.13
     raw
    0.13
    oning
    0.13
    /
    0.13
    的
    0.13
    able
    0.13
    POSITIVE LOGITS
    áus
    0.16
     variabili
    0.15
     extrêmement
    0.15
    літи
    0.15
     estremamente
    0.15
     variáveis
    0.15
     variável
    0.15
    쥘
    0.15
     अत्यंत
    0.15
    ඩු
    0.15
    Activations Density 0.003%

    No Known Activations