© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175760
    Prev
    Next
    INDEX
    Explanations

    B variations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Nobody
    0.36
    uffin
    0.36
    க்குக
    0.36
     Shap
    0.36
    AlH
    0.35
     SH
    0.34
     N
    0.33
     AL
    0.33
     Chen
    0.33
     Fate
    0.33
    POSITIVE LOGITS
     B
    0.63
    Ｂ
    0.59
    B
    0.55
     บ
    0.52
    𝐵
    0.51
     Б
    0.49
     الب
    0.48
     ब
    0.47
     बी
    0.46
     Bany
    0.45
    Activations Density 0.000%

    No Known Activations