© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19586
    Prev
    Next
    INDEX
    Explanations

    Carlton, Bondi, Botafogo, Waikiki

    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_15_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
     montrent
    0.27
     montrer
    0.26
     göst
    0.23
     atteindre
    0.23
     efeitos
    0.23
    addWidget
    0.22
     ಇನ್ನೂ
    0.22
    eraient
    0.22
     那麼
    0.22
    ]，
    0.22
    POSITIVE LOGITS
    Lok
    0.23
    Physics
    0.22
    Vehicle
    0.22
    Res
    0.21
    Art
    0.21
    En
    0.21
    Ak
    0.21
    Kos
    0.21
    International
    0.21
    ས
    0.21
    Activations Density 0.004%

    No Known Activations