© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207041
    Prev
    Next
    INDEX
    Explanations

    parentheses and specific words

    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_10_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
     confidence
    0.49
    .")
    0.49
     congestion
    0.49
    C
    0.47
     t
    0.47
    .')
    0.47
     society
    0.46
     \
    0.46
    С
    0.46
     caos
    0.46
    POSITIVE LOGITS
    ærer
    0.59
    ain
    0.57
     ejercer
    0.56
    ecz
    0.55
    érence
    0.53
    eer
    0.53
    ű
    0.52
    ard
    0.52
    ulc
    0.52
    <unused348>
    0.52
    Activations Density 0.000%

    No Known Activations