© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246459
    Prev
    Next
    INDEX
    Explanations

    contractions and punctuation

    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_40_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
    <unused31>
    0.47
    infused
    0.45
    articles
    0.41
     infused
    0.41
    <unused83>
    0.41
    infested
    0.41
     JO
    0.40
    <unused34>
    0.40
    <unused30>
    0.39
     capitalized
    0.39
    POSITIVE LOGITS
     দায়
    0.42
     Hedge
    0.36
     Reported
    0.36
    Hint
    0.36
     Riddle
    0.36
    Selective
    0.36
     تقری
    0.36
     sequence
    0.35
    Accuracy
    0.35
     fussy
    0.35
    Activations Density 0.005%

    No Known Activations