© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166636
    Prev
    Next
    INDEX
    Explanations

    causes of problems

    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_34_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
    Everyone
    0.43
    για
    0.41
     ปก
    0.41
    สำหรับ
    0.40
     व्र
    0.40
    흔
    0.39
    amiseks
    0.39
    anyone
    0.38
    স্তন
    0.38
    Box
    0.38
    POSITIVE LOGITS
     Kyrgyz
    0.38
    აც
    0.36
    йки
    0.35
     proporcional
    0.35
    <0xAA>
    0.34
     dovrà
    0.33
    spaper
    0.33
     Initializes
    0.33
     schafft
    0.33
     iniciado
    0.32
    Activations Density 0.004%

    No Known Activations