© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38245
    Prev
    Next
    INDEX
    Explanations

    ge

    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_57_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
     га
    1.63
     Has
    1.61
    Has
    1.45
     Га
    1.41
    has
    1.24
    Га
    1.24
    ガ
    1.20
     가
    1.13
    HAS
    1.09
     HAS
    1.09
    POSITIVE LOGITS
     ге
    1.86
     gé
    1.59
    ge
    1.41
     Ge
    1.39
     GE
    1.38
     Ге
    1.36
    Ге
    1.35
     ge
    1.34
    Ge
    1.34
    ге
    1.33
    Activations Density 0.006%

    No Known Activations