© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205803
    Prev
    Next
    INDEX
    Explanations

    foreign scripts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Fund
    0.41
    Fach
    0.38
     Soap
    0.37
     یورپی
    0.37
     Sai
    0.36
     Slack
    0.36
    졔
    0.36
     Andri
    0.36
    ירים
    0.36
     U
    0.36
    POSITIVE LOGITS
     propyl
    0.43
    鮎
    0.41
    ást
    0.40
    丙
    0.39
     พ
    0.38
    ետ
    0.38
     алу
    0.38
    辶
    0.38
    дою
    0.38
    স্তা
    0.37
    Activations Density 0.000%

    No Known Activations