© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102616
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    市
    0.23
    Экс
    0.19
     centre
    0.19
    Con
    0.19
    Electron
    0.18
     retracted
    0.18
    Micro
    0.18
    Qty
    0.18
     optimisation
    0.18
    াড়ার
    0.18
    POSITIVE LOGITS
    nson
    0.22
    <unused1053>
    0.21
    <unused678>
    0.20
    㷫
    0.20
     ベージュ
    0.20
    <unused331>
    0.19
     ม
    0.19
    SpriteCollision
    0.19
    <unused593>
    0.19
     Մ
    0.19
    Activations Density 0.007%

    No Known Activations