© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234816
    Prev
    Next
    INDEX
    Explanations

    structured data

    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_32_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
    {
    0.36
    interpret
    0.33
     regina
    0.32
    мун
    0.32
    Faster
    0.31
     γά
    0.31
    customize
    0.30
     axs
    0.29
    iceras
    0.29
    triple
    0.29
    POSITIVE LOGITS
    }={\
    0.35
     Gayle
    0.34
    वें
    0.34
     undeniable
    0.34
     imaginable
    0.33
     incredible
    0.33
     admittedly
    0.32
     Apare
    0.32
     uzn
    0.32
    盻
    0.32
    Activations Density 0.001%

    No Known Activations