© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102464
    Prev
    Next
    INDEX
    Explanations

    hosted platforms

    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_16_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
    新型コロナ
    0.54
     Enquanto
    0.53
     wrecked
    0.52
     organizada
    0.51
     Schatten
    0.50
     vogliamo
    0.49
    𒋼
    0.49
     gleiche
    0.48
    ݢ
    0.48
     Luego
    0.47
    POSITIVE LOGITS
    ė
    0.54
    m
    0.52
    oss
    0.52
    pil
    0.51
    under
    0.49
    vad
    0.47
    olen
    0.47
    iter
    0.46
    urring
    0.46
    ahar
    0.46
    Activations Density 0.000%

    No Known Activations