© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44134
    Prev
    Next
    INDEX
    Explanations

    DARPA

    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_13_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
     kurzer
    0.51
    и
    0.50
     valuation
    0.49
     clause
    0.47
     rey
    0.47
     staked
    0.47
    ина
    0.45
     expresar
    0.45
    েই
    0.44
     refuse
    0.44
    POSITIVE LOGITS
     ప్రజ
    0.50
    digit
    0.50
    álás
    0.49
    pInBuffer
    0.49
    daar
    0.48
    گر
    0.48
    (-
    0.47
    da
    0.47
    (...
    0.46
    nummer
    0.46
    Activations Density 0.001%

    No Known Activations