© 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. 198982
    Prev
    Next
    INDEX
    Explanations

    React component declarations

    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
     ecuaciones
    0.31
    ച്
    0.30
    緋
    0.29
    mutable
    0.28
    Mutability
    0.28
    Outcome
    0.28
    Positions
    0.27
    Infinity
    0.27
    realistic
    0.27
    Balancer
    0.27
    POSITIVE LOGITS
     TIPS
    0.31
    Mq
    0.29
     zaken
    0.28
     Przed
    0.28
     nati
    0.27
    屋
    0.27
     श्रेष्ठ
    0.27
     Outfitters
    0.27
    ٗ
    0.27
     Expert
    0.27
    Activations Density 0.000%

    No Known Activations