© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235922
    Prev
    Next
    INDEX
    Explanations

    distance units

    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_25_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
    Subset
    0.42
     contradicting
    0.41
     unfortunate
    0.37
    ध
    0.35
     inciting
    0.35
     unchanging
    0.35
    矛盾
    0.34
     ಇದಕ್ಕೆ
    0.34
     conflicting
    0.34
    으로부터
    0.34
    POSITIVE LOGITS
    आईएस
    0.41
    阪
    0.40
    Turkish
    0.40
     इस्तेमाल
    0.39
    Institut
    0.38
     खातों
    0.38
    AuthProvider
    0.38
     JUN
    0.37
     জেনারেল
    0.37
     \"%
    0.36
    Activations Density 0.000%

    No Known Activations