© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51708
    Prev
    Next
    INDEX
    Explanations

    specific impulse, weight, power, heat, gravity, speeds

    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_30_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
    likely
    0.26
    irting
    0.26
    érg
    0.25
    豈
    0.25
    galaxys
    0.24
    ⩽
    0.24
    甬
    0.24
    ⁄
    0.24
    loid
    0.23
    mba
    0.23
    POSITIVE LOGITS
     specific
    0.32
     Specific
    0.29
     detailed
    0.29
     masses
    0.28
     specifics
    0.27
     spezif
    0.27
    specific
    0.27
     deta
    0.26
    具体的
    0.26
     Sue
    0.26
    Activations Density 0.001%

    No Known Activations