© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89600
    Prev
    Next
    INDEX
    Explanations

    damp

    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_11_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
    ša
    0.64
    f
    0.64
    ều
    0.63
    st
    0.61
     goddess
    0.60
    <\
    0.60
     Chúng
    0.58
    𒊩
    0.58
    ní
    0.57
    ŋ
    0.57
    POSITIVE LOGITS
    З
    0.68
    близи
    0.63
    Б
    0.61
    ОР
    0.61
    IPPING
    0.60
    ANIM
    0.60
    М
    0.58
     діяльності
    0.58
     варто
    0.58
    ین
    0.57
    Activations Density 0.002%

    No Known Activations