© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235386
    Prev
    Next
    INDEX
    Explanations

    through something

    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_32_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
     ಬಳ
    0.43
     digestibility
    0.38
     forwarding
    0.38
    说什么
    0.38
    ྷ
    0.38
    SeekBar
    0.38
     considerations
    0.37
     plod
    0.37
    济
    0.37
     requirements
    0.36
    POSITIVE LOGITS
     Fokus
    0.39
     foco
    0.38
     Bang
    0.37
     fokus
    0.36
    businessman
    0.36
    mmol
    0.35
     Ionic
    0.34
     Bacon
    0.34
    Equ
    0.34
    ُمْ
    0.34
    Activations Density 0.005%

    No Known Activations