© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116845
    Prev
    Next
    INDEX
    Explanations

    discord commands

    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_27_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
    Mind
    0.32
    ському
    0.32
     আদাল
    0.32
    面前
    0.32
    煩
    0.31
     cytokines
    0.31
     bers
    0.30
    ської
    0.30
    QQ
    0.30
    ולנד
    0.30
    POSITIVE LOGITS
     Farbe
    0.33
     Stable
    0.29
     Strawberry
    0.29
     Not
    0.29
     न
    0.28
     colored
    0.28
     Brim
    0.28
     Black
    0.28
     જવાબ
    0.28
     ("
    0.28
    Activations Density 0.001%

    No Known Activations