© 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. 206573
    Prev
    Next
    INDEX
    Explanations

    question

    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
    ඖ
    0.40
    滹
    0.38
    凹
    0.38
    appointments
    0.37
     ट्यूब
    0.37
    チ
    0.36
     Wood
    0.36
    OLOGIA
    0.36
    议
    0.36
     gia
    0.36
    POSITIVE LOGITS
     questioning
    2.36
     questioned
    2.33
    question
    1.80
    Question
    1.80
     Question
    1.77
     questionnaire
    1.77
     cuestion
    1.76
     QUESTION
    1.75
     question
    1.74
     Questionnaire
    1.74
    Activations Density 0.001%

    No Known Activations