© 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. 258514
    Prev
    Next
    INDEX
    Explanations

    out of 5 stars

    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
    提起
    0.45
     powierzchn
    0.43
     desn
    0.41
    来看看
    0.40
    땐
    0.39
    riwal
    0.39
    𝐗
    0.39
     분석
    0.38
    楧
    0.38
     fonti
    0.38
    POSITIVE LOGITS
     described
    0.43
     ایسی
    0.42
    iPad
    0.42
     মেঝে
    0.38
    described
    0.38
    продук
    0.37
     между
    0.36
    📪
    0.36
    Strawberry
    0.36
    azes
    0.36
    Activations Density 0.003%

    No Known Activations