© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36778
    Prev
    Next
    INDEX
    Explanations

    edgar allan poe

    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
    il
    0.68
     spolu
    0.64
    s
    0.59
     UBC
    0.59
     ROUILLER
    0.58
    ‌است
    0.58
     IRL
    0.58
    薛
    0.57
    áž
    0.57
     persoon
    0.57
    POSITIVE LOGITS
    و
    0.82
    {
    0.79
    (
    0.78
    ۸
    0.65
    ምት
    0.64
    ق
    0.64
    ו
    0.64
    ваме
    0.63
    ۳
    0.63
    ޏ
    0.63
    Activations Density 0.000%

    No Known Activations