© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4469
    Prev
    Next
    INDEX
    Explanations

    you want to

    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_39_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
    ํ
    0.44
    Everything
    0.42
    Flavor
    0.40
     স্থাপন
    0.39
    瘴
    0.39
     Everything
    0.38
     enormes
    0.38
    ఙ
    0.37
     แจ
    0.37
     posséd
    0.37
    POSITIVE LOGITS
     guess
    0.44
    чению
    0.40
    装置
    0.40
    ber
    0.40
     hire
    0.40
    ranet
    0.39
     tatt
    0.39
    unj
    0.38
    джер
    0.38
    ビネット
    0.38
    Activations Density 0.140%

    No Known Activations