© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202339
    Prev
    Next
    INDEX
    Explanations

    fundamental concepts

    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
    LIOGRAPHY
    0.39
    ழுது
    0.36
     waterline
    0.36
     hep
    0.36
    ற்ப
    0.36
    껑
    0.35
    oscope
    0.35
    攫
    0.35
     culturales
    0.35
     corrosion
    0.34
    POSITIVE LOGITS
     continuously
    0.46
    事项
    0.44
     constantly
    0.42
     постоянно
    0.42
     отмечает
    0.40
    的表现
    0.39
     Christchurch
    0.38
    NUM
    0.38
     ständig
    0.38
     constantemente
    0.38
    Activations Density 0.010%

    No Known Activations