© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9151
    Prev
    Next
    INDEX
    Explanations

    college student

    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_40_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
     sworn
    0.36
     صحی
    0.36
    тол
    0.36
     Britannica
    0.35
     Bean
    0.35
    螈
    0.35
    FBSDKSettings
    0.35
     bean
    0.34
    ნ
    0.34
    ння
    0.33
    POSITIVE LOGITS
     students
    0.82
     Students
    0.80
    Students
    0.80
     student
    0.77
    学生
    0.77
     STUDENTS
    0.77
    學生
    0.76
    学生的
    0.75
    students
    0.73
    Student
    0.71
    Activations Density 0.016%

    No Known Activations