© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3389
    Prev
    Next
    INDEX
    Explanations

    'd' sound

    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_39_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
    स्फ
    0.45
    icent
    0.43
    χρι
    0.39
     शासित
    0.39
    ෂ
    0.39
    <0xEC>
    0.38
    )^{-\
    0.37
     நிச்ச
    0.37
     ткани
    0.37
    ष्क
    0.37
    POSITIVE LOGITS
    Editor
    0.43
    loved
    0.42
     ಬೀ
    0.38
     ወደ
    0.38
     Editor
    0.37
     Nd
    0.37
     editor
    0.37
    good
    0.37
     d
    0.36
    Spanish
    0.36
    Activations Density 0.017%

    No Known Activations