© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17459
    Prev
    Next
    INDEX
    Explanations

    cars

    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
     reprim
    0.46
     Bols
    0.45
     Kidman
    0.44
     Rusia
    0.43
    🍈
    0.43
    ‼
    0.42
     invoice
    0.42
    FRINGEMENT
    0.41
     Merriam
    0.41
    ▹
    0.41
    POSITIVE LOGITS
    ён
    0.45
    red
    0.42
     第
    0.41
    ello
    0.41
    redi
    0.41
    able
    0.40
    adores
    0.40
    楝
    0.40
    люб
    0.40
    主要
    0.39
    Activations Density 0.010%

    No Known Activations