© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45038
    Prev
    Next
    INDEX
    Explanations

    incremental number, cause of, subsequent turn

    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_13_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
    erin
    0.50
    زل
    0.49
    enciais
    0.47
    л
    0.46
     areal
    0.46
     edil
    0.45
     inconsider
    0.45
    нг
    0.45
    ，
    0.45
    狠
    0.45
    POSITIVE LOGITS
     njegov
    0.56
     മുഹമ്മ
    0.55
    곽
    0.55
     zbog
    0.53
    ধারী
    0.52
    UpperBound
    0.51
     tracker
    0.50
     পাকিস্তানের
    0.50
    ()).
    0.50
    Когда
    0.49
    Activations Density 0.000%

    No Known Activations