© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14330
    Prev
    Next
    INDEX
    Explanations

    Computer Associates or death

    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_13_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
    }):
    0.12
    Methyl
    0.11
     верши
    0.11
    етки
    0.11
    ORIAL
    0.11
    ет
    0.11
    ори
    0.11
     ورک
    0.11
    IFIED
    0.10
    ौरी
    0.10
    POSITIVE LOGITS
    t
    0.13
     chandelier
    0.12
     chandeliers
    0.12
     scam
    0.12
     chipset
    0.11
     macrophage
    0.11
    sns
    0.11
    may
    0.11
     tulle
    0.11
     GLA
    0.11
    Activations Density 0.003%

    No Known Activations