© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154917
    Prev
    Next
    INDEX
    Explanations

    da

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    yata
    0.36
    ደረ
    0.36
    atum
    0.35
    }-(
    0.35
     infile
    0.35
     عص
    0.35
    鿓
    0.35
     Vit
    0.35
    uum
    0.34
    ؏
    0.34
    POSITIVE LOGITS
     da
    1.84
     да
    1.49
    Da
    1.27
    da
    1.22
     Da
    1.21
     دا
    1.13
     DA
    1.09
    DA
    0.96
    دا
    0.92
     दा
    0.92
    Activations Density 0.001%

    No Known Activations