© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7326
    Prev
    Next
    INDEX
    Explanations

    Q and subsequent characters

    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
    icill
    0.41
     zipcode
    0.36
    游
    0.35
    answer
    0.34
    zip
    0.34
     الارد
    0.33
    Keeping
    0.32
     zip
    0.32
     ap
    0.31
    tting
    0.31
    POSITIVE LOGITS
     Q
    1.09
    Q
    0.93
    Ｑ
    0.93
     Qo
    0.91
     Qu
    0.89
     QQ
    0.86
     QV
    0.86
     q
    0.84
     Qe
    0.82
    Ql
    0.81
    Activations Density 0.105%

    No Known Activations