© 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. 243874
    Prev
    Next
    INDEX
    Explanations

    test success messages

    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
    chelles
    0.42
    射
    0.39
     Rubin
    0.38
     መጠቀም
    0.38
     واقف
    0.37
    δικ
    0.37
    ensee
    0.36
    arbeiter
    0.36
    isPreview
    0.35
    ര്‍ക്കും
    0.35
    POSITIVE LOGITS
     ran
    0.55
     runs
    0.44
     run
    0.42
     Passing
    0.40
     pasar
    0.39
    䨪
    0.39
     Ran
    0.39
     NIM
    0.39
     running
    0.38
     Skor
    0.38
    Activations Density 0.000%

    No Known Activations