© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124251
    Prev
    Next
    INDEX
    Explanations

    fresh or better

    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_3_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
    er
    0.91
    t
    0.80
    ä
    0.79
    4
    0.77
    yd
    0.73
    tion
    0.73
    ne
    0.72
    nd
    0.71
    arak
    0.71
    ر
    0.71
    POSITIVE LOGITS
    ين
    0.89
     ofrecen
    0.81
     construye
    0.81
     avanzar
    0.81
     vayan
    0.80
    しても
    0.80
     dejaron
    0.79
     aceptar
    0.77
     suelo
    0.77
     asegurar
    0.77
    Activations Density 0.000%

    No Known Activations