© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54366
    Prev
    Next
    INDEX
    Explanations

    responsibilities and examples

    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_31_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
     Fake
    0.41
    Fake
    0.40
     ns
    0.36
     fake
    0.35
    Inicial
    0.34
     नकली
    0.34
     Inicial
    0.34
    煲
    0.32
    Artificial
    0.32
     Idiot
    0.32
    POSITIVE LOGITS
    提供的
    0.34
    垮
    0.34
     providing
    0.33
     outnumbered
    0.32
    asion
    0.32
    сиона
    0.32
    サロン
    0.31
     paying
    0.31
     salon
    0.31
     membayar
    0.31
    Activations Density 0.016%

    No Known Activations