© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45239
    Prev
    Next
    INDEX
    Explanations

    before/pre exercise

    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_22_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
     before
    0.46
     قبل
    0.43
    uatu
    0.43
    Before
    0.42
    Weeks
    0.40
     after
    0.40
     ह
    0.39
    :",
    0.39
     petal
    0.39
    ⁧
    0.39
    POSITIVE LOGITS
     fossils
    0.41
     Mesmo
    0.41
    fontein
    0.41
    korzyst
    0.40
    asyarakat
    0.40
     disobedience
    0.40
     levando
    0.39
    ogaster
    0.39
     légion
    0.39
    घाडी
    0.39
    Activations Density 0.003%

    No Known Activations