© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85771
    Prev
    Next
    INDEX
    Explanations

    cupcake

    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_3_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
    них
    0.83
    ת
    0.79
    す
    0.77
    ล
    0.75
    j
    0.74
    larında
    0.73
    ू
    0.72
    的な
    0.71
    um
    0.71
    리
    0.71
    POSITIVE LOGITS
     tinnitus
    0.66
     psoriasis
    0.66
     fibrosis
    0.65
    tare
    0.62
    oirs
    0.62
    pré
    0.62
    tedir
    0.61
     biot
    0.61
     Revolución
    0.61
     genet
    0.61
    Activations Density 0.000%

    No Known Activations