© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210025
    Prev
    Next
    INDEX
    Explanations

    stock prices

    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_20_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
    傊
    0.49
     incluye
    0.48
     includes
    0.46
     recognises
    0.46
     ниж
    0.45
     bahasa
    0.45
     utbild
    0.44
     maraming
    0.44
     incorporates
    0.44
     equatorial
    0.44
    POSITIVE LOGITS
    jer
    0.45
    </tr>
    0.41
    Bey
    0.39
    Palette
    0.39
    lty
    0.39
    fprintf
    0.38
    juna
    0.38
    boolean
    0.38
    ge
    0.37
     Σε
    0.37
    Activations Density 0.003%

    No Known Activations