© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120428
    Prev
    Next
    INDEX
    Explanations

    specific phrases or entities

    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_27_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
    ldre
    0.38
    吮
    0.37
    áték
    0.37
    yeri
    0.35
    ller
    0.35
    erry
    0.35
    𒁍
    0.34
    🙉
    0.34
    gangenheit
    0.33
    瘍
    0.33
    POSITIVE LOGITS
     University
    0.34
     university
    0.32
     Jesuit
    0.32
     American
    0.31
     Form
    0.31
    issimo
    0.31
     Yup
    0.31
     Tham
    0.31
     MIT
    0.31
    ブラック
    0.30
    Activations Density 0.010%

    No Known Activations