© 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. 40332
    Prev
    Next
    INDEX
    Explanations

    counter narrative

    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
     قریب
    0.56
     résident
    0.50
    ಿದೆ
    0.49
     invokes
    0.49
     réduite
    0.49
    ು
    0.47
    ALT
    0.46
    تمع
    0.46
     Baill
    0.46
     previs
    0.46
    POSITIVE LOGITS
    esting
    0.58
    ن
    0.58
    it
    0.57
    ebilir
    0.54
    /
    0.53
    ica
    0.52
    on
    0.51
     недоста
    0.51
    al
    0.51
    andez
    0.51
    Activations Density 0.000%

    No Known Activations