© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137439
    Prev
    Next
    INDEX
    Explanations

    game names like Apex Legends or Fortnite

    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_12_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
    th
    0.12
    D
    0.12
    â
    0.12
    B
    0.12
    F
    0.12
    U
    0.12
    ();
    0.11
    6
    0.11
    0
    0.11
     குற்றம்
    0.11
    POSITIVE LOGITS
     lorsque
    0.13
     kurzer
    0.12
    কর
    0.11
     selaku
    0.11
    нами
    0.11
     kleinere
    0.10
    謦
    0.10
    ون
    0.10
    он
    0.10
    нала
    0.10
    Activations Density 0.002%

    No Known Activations