© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207032
    Prev
    Next
    INDEX
    Explanations

    selection import

    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_19_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
    қ
    0.59
    パラメータ
    0.49
     ап
    0.47
    Descripción
    0.47
    Limitations
    0.47
    Benzyl
    0.47
    Manipulation
    0.47
    Arbit
    0.46
    Referee
    0.46
    п
    0.45
    POSITIVE LOGITS
     what
    0.51
    ោគ
    0.48
    衫
    0.45
     anybody
    0.45
    axies
    0.43
    irma
    0.42
     اهو
    0.42
    শস্ত্র
    0.42
     whatever
    0.41
     indigestion
    0.41
    Activations Density 0.001%

    No Known Activations