© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26906
    Prev
    Next
    INDEX
    Explanations

    ScienceFocus articles

    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_40_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
     میچ
    0.42
     Notify
    0.40
     KUR
    0.37
    Hook
    0.36
    ∬
    0.36
     Io
    0.36
    UF
    0.36
     Midi
    0.35
     ಇನ್ನ
    0.35
    焽
    0.35
    POSITIVE LOGITS
     radio
    0.44
     astronomy
    0.42
     радио
    0.40
     Radio
    0.39
    module
    0.38
     பயன்படுத்த
    0.38
     petroleum
    0.38
    radio
    0.37
    ቲክ
    0.37
    oglobin
    0.37
    Activations Density 0.000%

    No Known Activations