© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 470
    Prev
    Next
    INDEX
    Explanations

    "that's a"

    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_40_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
    をして
    0.66
    をした
    0.62
     Doing
    0.60
    Doing
    0.60
    をしている
    0.60
    做
    0.59
    做了
    0.57
    做什么
    0.57
    做的
    0.56
     doing
    0.54
    POSITIVE LOGITS
     finish
    0.42
    Iso
    0.41
    噰
    0.39
    ikai
    0.38
    huis
    0.37
     Iso
    0.37
     toll
    0.36
     dials
    0.36
     elevates
    0.36
     finishes
    0.35
    Activations Density 0.001%

    No Known Activations