© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41021
    Prev
    Next
    INDEX
    Explanations

    confidence/knowledge/academic

    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_3_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
    ના
    0.98
    ни
    0.96
    ва
    0.89
    でした
    0.80
    ام
    0.79
    ને
    0.77
    на
    0.75
    Д
    0.75
    houses
    0.74
    ină
    0.72
    POSITIVE LOGITS
    .
    0.86
    AI
    0.73
    ב
    0.65
    ou
    0.63
    Ext
    0.62
    ilan
    0.62
     ET
    0.59
    ARE
    0.59
    玨
    0.58
     Motivational
    0.58
    Activations Density 0.008%

    No Known Activations