© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14825
    Prev
    Next
    INDEX
    Explanations

    hallucinations or imagining

    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_13_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
     utopian
    0.59
     चांग
    0.55
     ప్రత్యేక
    0.55
    โยชน์
    0.55
    явления
    0.54
     떨
    0.53
     thụ
    0.52
     étro
    0.51
    䢂
    0.51
     représentent
    0.50
    POSITIVE LOGITS
    _
    0.61
    ן
    0.59
     Automotive
    0.58
     mah
    0.56
    Mah
    0.56
    *
    0.55
    mah
    0.54
    Bird
    0.54
    Procedure
    0.54
    م
    0.54
    Activations Density 0.104%

    No Known Activations