© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40182
    Prev
    Next
    INDEX
    Explanations

    recalling information

    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_11_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
    𝐟
    0.65
    ON
    0.63
    𝐱
    0.62
    كر
    0.61
     imprese
    0.61
    Number
    0.59
     الفريق
    0.59
    𝐅
    0.59
    في
    0.58
    K
    0.58
    POSITIVE LOGITS
     contradicts
    0.64
     wanting
    0.64
    ু
    0.62
    erne
    0.54
    ्य
    0.54
     потребу
    0.52
     sockets
    0.51
     तिथे
    0.51
    le
    0.50
     trying
    0.50
    Activations Density 0.002%

    No Known Activations