© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39825
    Prev
    Next
    INDEX
    Explanations

    notes

    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_11_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
    meh
    0.62
    agonal
    0.60
    anganese
    0.59
    c
    0.57
    オ
    0.55
    only
    0.54
    ע
    0.53
    ahorse
    0.52
    ו
    0.52
    ならない
    0.51
    POSITIVE LOGITS
    रेक्ट
    0.54
    拷
    0.51
    
    0.49
     ecu
    0.49
     Contin
    0.49
    噜
    0.48
    壹百
    0.47
    𝟑
    0.47
    ige
    0.47
     വഴ
    0.47
    Activations Density 0.003%

    No Known Activations