© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149780
    Prev
    Next
    INDEX
    Explanations

    Seven Wonders, guarded, Toxic People, unrealistic

    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_23_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
     Switzerland
    0.42
     switched
    0.40
     countries
    0.38
     surprise
    0.38
     technique
    0.38
    鈕
    0.38
     Swiss
    0.37
     period
    0.37
     Area
    0.37
    ച്ചു
    0.37
    POSITIVE LOGITS
    하지만
    0.43
    =-
    0.42
     แรก
    0.41
    멱
    0.40
    衵
    0.40
     =-
    0.39
     하지만
    0.39
    empot
    0.39
     সঙ্গীত
    0.39
    但他
    0.38
    Activations Density 0.000%

    No Known Activations