© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86316
    Prev
    Next
    INDEX
    Explanations

    than you think

    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_18_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
     nurseries
    0.51
     व
    0.49
    فت
    0.46
     பல்கலைக்கழக
    0.46
     rankings
    0.46
     along
    0.46
     weekly
    0.46
     above
    0.46
    色
    0.45
     پیر
    0.45
    POSITIVE LOGITS
    idi
    0.59
    ỹ
    0.50
     ولكن
    0.49
    ḧ
    0.49
    Context
    0.48
     idi
    0.47
    onu
    0.46
    '_{
    0.45
    *%
    0.45
     Context
    0.45
    Activations Density 0.002%

    No Known Activations