© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51845
    Prev
    Next
    INDEX
    Explanations

    code string manipulation

    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_31_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
    ):["
    0.42
    =["
    0.41
    añas
    0.40
    짙
    0.37
    ={"
    0.37
    Mouse
    0.36
    肢
    0.35
    ⓒ
    0.35
     महा
    0.35
    ídas
    0.35
    POSITIVE LOGITS
     რამდ
    0.38
    restaurant
    0.36
    training
    0.36
    евского
    0.35
    rnn
    0.35
    𝚢
    0.35
    emek
    0.35
    reactive
    0.35
     lymphocyte
    0.34
    educational
    0.33
    Activations Density 0.091%

    No Known Activations