© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193298
    Prev
    Next
    INDEX
    Explanations

    map here

    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_27_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
    LIED
    0.39
    RF
    0.39
     kommenden
    0.38
     dijual
    0.38
    Dod
    0.37
     शोर
    0.36
     pengembangan
    0.36
     Роди
    0.36
    स्रोत
    0.36
    𝙶
    0.36
    POSITIVE LOGITS
    খালী
    0.43
     expend
    0.37
     exoner
    0.35
     TOS
    0.34
    ებას
    0.33
     Ten
    0.32
     Assets
    0.32
     long
    0.32
     fins
    0.32
    ToJava
    0.32
    Activations Density 0.000%

    No Known Activations