© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4576
    Prev
    Next
    INDEX
    Explanations

    yoga and remedies

    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_38_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
     allocates
    0.46
    ignores
    0.43
     Lur
    0.41
     allocated
    0.40
     bistro
    0.38
    simulator
    0.38
    AUX
    0.38
    宾
    0.38
     exponentes
    0.38
     ஒது
    0.38
    POSITIVE LOGITS
    杲
    0.41
     उपाय
    0.39
     Pach
    0.39
     App
    0.38
     upay
    0.37
     remedies
    0.36
    lič
    0.36
     kapp
    0.35
    corre
    0.35
     মহ
    0.34
    Activations Density 0.033%

    No Known Activations