© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63794
    Prev
    Next
    INDEX
    Explanations

    Cha

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     차
    2.05
    차
    1.84
    车
    1.84
    車
    1.78
     车
    1.61
    차가
    1.55
    的车
    1.53
    车的
    1.50
     car
    1.46
     車
    1.42
    POSITIVE LOGITS
    Urs
    0.42
    Ec
    0.39
    bli
    0.38
    cis
    0.38
     Aqua
    0.36
    vf
    0.36
    जब
    0.35
    viv
    0.34
    Alz
    0.34
    vc
    0.33
    Activations Density 0.001%

    No Known Activations