© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175291
    Prev
    Next
    INDEX
    Explanations

    being held, becoming, available

    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_20_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
    modelo
    0.51
     estudio
    0.50
    vento
    0.46
    iguiente
    0.45
     niño
    0.44
     Estudio
    0.44
    о
    0.44
    ्च
    0.43
     생각
    0.43
    roductive
    0.42
    POSITIVE LOGITS
     Bromley
    0.41
    зін
    0.40
     Boogie
    0.40
     frustration
    0.39
     Bevan
    0.38
     Carrie
    0.38
     男性用
    0.38
     lorsqu
    0.38
    ត់
    0.38
     Feder
    0.37
    Activations Density 0.019%

    No Known Activations