© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205962
    Prev
    Next
    INDEX
    Explanations

    any remaining

    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_37_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
    天井
    0.40
     செலு
    0.38
    太陽
    0.37
     aqu
    0.37
     पका
    0.35
    啊
    0.35
     aq
    0.34
    leş
    0.34
    太阳
    0.34
    アク
    0.34
    POSITIVE LOGITS
     thing
    0.50
     것에
    0.44
     ones
    0.44
     coordination
    0.42
    ものは
    0.42
     것
    0.42
     tume
    0.41
     bagay
    0.39
     coordinating
    0.38
    hosts
    0.38
    Activations Density 0.004%

    No Known Activations