© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10896
    Prev
    Next
    INDEX
    Explanations

    jeep, tribal, bandit, tenure

    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
     belajar
    0.57
    %。
    0.54
    。)
    0.53
    Krishna
    0.53
    后端
    0.51
     جهان
    0.51
    نسان
    0.51
    ۔
    0.51
     انسان
    0.50
     وزار
    0.50
    POSITIVE LOGITS
     publication
    0.49
    িবে
    0.47
     obscures
    0.45
    registr
    0.44
     hiring
    0.43
     com
    0.42
    hen
    0.42
    ့်
    0.42
    éndose
    0.42
     provoke
    0.42
    Activations Density 0.011%

    No Known Activations