© 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. 49785
    Prev
    Next
    INDEX
    Explanations

    list item start

    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
     此
    0.26
    对此
    0.26
    のみ
    0.25
     Namun
    0.24
    ინგ
    0.24
    的点
    0.23
    感知
    0.23
    Baseline
    0.22
    Namun
    0.22
     azide
    0.22
    POSITIVE LOGITS
    SMA
    0.24
    ጀመሪያ
    0.22
     runner
    0.22
     խ
    0.22
    ávy
    0.21
    வ்வளவு
    0.21
    SUFFIX
    0.21
     SMA
    0.21
     परेशानियों
    0.21
    heiz
    0.21
    Activations Density 0.100%

    No Known Activations