© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228308
    Prev
    Next
    INDEX
    Explanations

    leave your luggage

    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_6_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
     apartamentos
    1.04
     apartamento
    0.92
     elegante
    0.91
    ки
    0.88
    те
    0.86
     avevano
    0.84
     L
    0.84
     desconocido
    0.84
     was
    0.83
     appartamento
    0.83
    POSITIVE LOGITS
    。
    1.22
    ।
    1.10
    tu
    1.09
    。"
    1.05
    ۔
    0.99
    st
    0.92
    to
    0.92
    ten
    0.92
    ።
    0.91
    ta
    0.89
    Activations Density 0.000%

    No Known Activations