© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46506
    Prev
    Next
    INDEX
    Explanations

    Sequential Read/Write speeds

    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
    Negative Logits
    選択
    0.20
     Flug
    0.17
    コード
    0.17
     Augen
    0.17
     Geist
    0.16
     Polite
    0.16
     Nachricht
    0.16
    暾
    0.16
     Begriff
    0.16
    主義
    0.16
    POSITIVE LOGITS
     श
    0.16
     bridged
    0.16
    COMB
    0.16
    每年
    0.16
     counterfeit
    0.16
    bridge
    0.15
     uph
    0.15
    श्न
    0.15
     हाश
    0.15
    🏎
    0.15
    Activations Density 0.011%

    No Known Activations