© 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. 205499
    Prev
    Next
    INDEX
    Explanations

    list items and deadlines

    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
    傛
    0.44
     اعظم
    0.42
    忝
    0.41
     सना
    0.39
     mette
    0.38
    luent
    0.38
     그렇지
    0.37
     Бы
    0.36
    hiyam
    0.36
    직
    0.36
    POSITIVE LOGITS
    dal
    0.39
    
    0.38
    ల
    0.38
    ūra
    0.37
    $\
    0.37
    Collaboration
    0.36
    Dal
    0.36
    OTA
    0.35
     लाभकारी
    0.35
    Coffee
    0.34
    Activations Density 0.002%

    No Known Activations