© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25485
    Prev
    Next
    INDEX
    Explanations

    aspirational futures and ideals

    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_10_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
     Hö
    0.55
     Hör
    0.54
     Dé
    0.52
     расстоянии
    0.52
     Þ
    0.52
     définit
    0.52
    Liv
    0.51
    Mét
    0.51
    Í
    0.51
     mód
    0.50
    POSITIVE LOGITS
    ہوں
    0.53
     proline
    0.50
     diarrhoea
    0.49
    бари
    0.48
     medias
    0.47
    umap
    0.47
     media
    0.46
     niacin
    0.46
    란
    0.45
    ्रेड
    0.45
    Activations Density 0.000%

    No Known Activations