© 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. 166988
    Prev
    Next
    INDEX
    Explanations

    find

    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
    лит
    0.40
     साक्षात्कार
    0.37
    គ្នា
    0.36
     accurate
    0.36
    ༈
    0.36
     tự
    0.35
     சிறப்பு
    0.35
    בק
    0.35
     сам
    0.35
     fuss
    0.34
    POSITIVE LOGITS
     writeFile
    0.37
    honia
    0.36
     Qualifier
    0.36
    Queen
    0.36
    Reactive
    0.35
    Locale
    0.35
    nemonic
    0.35
     Queen
    0.35
    ië
    0.35
    衬
    0.35
    Activations Density 0.007%

    No Known Activations