© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79553
    Prev
    Next
    INDEX
    Explanations

    current state, new developments

    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_31_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
    IRONMENT
    0.30
    racellular
    0.30
     создает
    0.30
     puts
    0.29
    uraea
    0.28
    emporal
    0.28
    shit
    0.28
    <li>
    0.27
    >((
    0.27
    relse
    0.27
    POSITIVE LOGITS
     tulips
    0.33
     harmonious
    0.33
     speakers
    0.32
     sunflowers
    0.32
     ሁሉም
    0.31
     xo
    0.31
     tokens
    0.30
     Dazu
    0.30
     axs
    0.29
    洵
    0.29
    Activations Density 0.014%

    No Known Activations