© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102944
    Prev
    Next
    INDEX
    Explanations

    code comments

    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_14_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    RIES
    0.47
    intentional
    0.44
    創作
    0.42
    涌
    0.42
    eller
    0.41
    PJ
    0.41
    eling
    0.41
    ной
    0.40
    species
    0.40
    ripe
    0.40
    POSITIVE LOGITS
    估计
    0.54
     szybko
    0.54
    掂
    0.54
    <0x07>
    0.53
     araşt
    0.53
    koe
    0.53
     obstacles
    0.52
    ]+/
    0.52
     destek
    0.52
    StillWater
    0.52
    Activations Density 0.000%

    No Known Activations