© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162509
    Prev
    Next
    INDEX
    Explanations

    引起/导致/引发 (cause/lead to)

    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_31_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
    esthetics
    0.42
    ))/(
    0.38
     STL
    0.37
    ໄລ
    0.37
    莽
    0.35
    esthetic
    0.35
     Critical
    0.34
    䂧
    0.34
     esth
    0.34
     Cancer
    0.34
    POSITIVE LOGITS
     हानि
    0.36
    πτωση
    0.36
    響
    0.36
     ocasiones
    0.35
     Zagre
    0.33
    andte
    0.33
     relacionado
    0.33
    綿
    0.32
     envelope
    0.32
     détail
    0.32
    Activations Density 0.000%

    No Known Activations