© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50560
    Prev
    Next
    INDEX
    Explanations

    props and Component context

    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_30_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
     തുട
    0.42
    ipio
    0.38
     кор
    0.37
    初回
    0.37
    デメリット
    0.36
    相
    0.35
    renn
    0.35
    zte
    0.35
    ﺟ
    0.35
     ಇನ್ನ
    0.34
    POSITIVE LOGITS
    isValid
    0.40
     contradictory
    0.40
     isValid
    0.39
    maßen
    0.39
     psychology
    0.39
     handled
    0.38
     startTime
    0.37
     incomparable
    0.37
    োদিত
    0.37
     optimizations
    0.37
    Activations Density 0.000%

    No Known Activations