© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208877
    Prev
    Next
    INDEX
    Explanations

    more, larger

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ဆုံး
    0.35
     Bader
    0.35
    Thin
    0.34
     Penta
    0.33
    锺
    0.33
    ಡ್
    0.32
     Thin
    0.32
     पूर्
    0.32
    ที่สุด
    0.32
    धीर
    0.32
    POSITIVE LOGITS
     gr
    3.25
    Gr
    2.94
     Gr
    2.78
    gr
    2.77
    格
    2.30
     ग्र
    2.20
     گر
    2.11
     GR
    2.08
     গ্র
    1.99
    GR
    1.96
    Activations Density 0.002%

    No Known Activations