© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98863
    Prev
    Next
    INDEX
    Explanations

    infection control

    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_14_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
    f
    0.53
    v
    0.47
    o
    0.46
     Weed
    0.46
     lait
    0.46
     usato
    0.45
    вара
    0.45
     হাসি
    0.45
    ана
    0.44
     Hat
    0.43
    POSITIVE LOGITS
     இஸ்
    0.46
     electromagnetic
    0.44
    )="
    0.42
    Cuánto
    0.42
     הל
    0.42
    త్‌
    0.41
     responds
    0.41
    Responsive
    0.41
    }$
    0.41
     الإسلام
    0.41
    Activations Density 0.002%

    No Known Activations