© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27424
    Prev
    Next
    INDEX
    Explanations

    describe, Scenario, it

    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
     Destinations
    0.43
     installers
    0.41
     fusing
    0.40
    Ḵ
    0.39
     shooters
    0.39
     destinations
    0.38
    লিক
    0.38
     মন্ত
    0.37
     shootings
    0.37
     visions
    0.36
    POSITIVE LOGITS
    Agriculture
    0.40
    geç
    0.39
    arden
    0.38
    울
    0.38
    Um
    0.38
    umbre
    0.37
    М
    0.37
    Ru
    0.36
    mount
    0.36
    물이
    0.35
    Activations Density 0.000%

    No Known Activations