© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237439
    Prev
    Next
    INDEX
    Explanations

    pharmaceuticals and stimulants

    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
    ),
    0.36
     Navier
    0.36
    }}-\
    0.35
     Ea
    0.35
     batter
    0.35
    фа
    0.35
     Inject
    0.34
    ouille
    0.34
    жной
    0.33
     Batter
    0.33
    POSITIVE LOGITS
     dermatology
    0.40
     majeur
    0.39
     事業
    0.38
    䄪
    0.38
    மானம்
    0.37
    ساوي
    0.36
     requieren
    0.35
     determina
    0.35
    思います
    0.35
     fixé
    0.35
    Activations Density 0.000%

    No Known Activations