© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161850
    Prev
    Next
    INDEX
    Explanations

    hadrons

    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_2_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
     has
    1.31
    dır
    0.96
    d
    0.92
     is
    0.90
     VOICE
    0.89
    z
    0.88
     in
    0.86
     bolsillo
    0.86
     područ
    0.85
    此同时
    0.84
    POSITIVE LOGITS
    (
    1.23
    itated
    1.11
    ва
    1.05
    یر
    1.04
    پور
    1.03
    erical
    1.02
    нда
    1.01
    arı
    1.01
    ње
    1.01
    ſe
    1.00
    Activations Density 0.000%

    No Known Activations