© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41258
    Prev
    Next
    INDEX
    Explanations

    fossil record

    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_11_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
    ęs
    0.55
    โ
    0.52
    ਕ
    0.52
    ”।
    0.51
    ം
    0.51
    ”:
    0.50
    یں
    0.49
    ի
    0.48
     decrees
    0.48
    逕
    0.48
    POSITIVE LOGITS
    ld
    0.53
    linux
    0.52
    Leo
    0.52
     }}
    0.50
     ','
    0.50
    ttl
    0.50
     начин
    0.50
    label
    0.49
    talk
    0.49
    Teach
    0.49
    Activations Density 0.000%

    No Known Activations