© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260595
    Prev
    Next
    INDEX
    Explanations

    realistic images

    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_22_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
    ដើម្បី
    0.15
     백
    0.13
    ך
    0.13
    ⑦
    0.13
     glPopMatrix
    0.13
     연구
    0.12
    ቂ
    0.12
     {\
    0.12
     галу
    0.12
    নব
    0.12
    POSITIVE LOGITS
     Н
    0.13
    Control
    0.13
    Celebr
    0.13
     mellan
    0.12
     spook
    0.12
     uint
    0.12
    uari
    0.12
     gemeinsame
    0.12
    jub
    0.12
    oplay
    0.12
    Activations Density 0.023%

    No Known Activations