© 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. 235231
    Prev
    Next
    INDEX
    Explanations

    student government

    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
     parental
    0.47
     parent
    0.47
    椎
    0.44
    parent
    0.41
    オペ
    0.40
     Parental
    0.40
     Parent
    0.39
    တင်
    0.39
     parents
    0.38
    Parent
    0.38
    POSITIVE LOGITS
     guard
    0.46
    Guard
    0.43
    guard
    0.42
    ры
    0.38
     Guard
    0.38
     feet
    0.38
    Ғ
    0.38
     fore
    0.37
    Mant
    0.36
     ಅನ್ನ
    0.36
    Activations Density 0.000%

    No Known Activations