© 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. 260096
    Prev
    Next
    INDEX
    Explanations

    code block markdown

    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
    ەد
    0.41
     배경
    0.39
     повторя
    0.36
     nevez
    0.36
     столи
    0.35
    sik
    0.35
    측
    0.35
     sufferings
    0.35
    निष्कर्ष
    0.35
     conclud
    0.35
    POSITIVE LOGITS
     Gauge
    0.39
    \
    0.38
    isotropic
    0.38
     espon
    0.38
    दै
    0.37
    worm
    0.37
    只限
    0.37
     Jahre
    0.37
     Genre
    0.37
    憾
    0.37
    Activations Density 0.000%

    No Known Activations