© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206028
    Prev
    Next
    INDEX
    Explanations

    know more about

    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_6_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
    ри
    1.17
    t
    1.02
     danni
    0.99
    اک
    0.93
     caracteres
    0.86
     tecnica
    0.86
     découverte
    0.84
     rapides
    0.84
    ิ
    0.84
    ג
    0.84
    POSITIVE LOGITS
    is
    1.05
     It
    0.95
    ning
    0.93
    తో
    0.88
    ja
    0.87
    with
    0.86
    was
    0.84
    ंनी
    0.80
     ”
    0.79
    :
    0.78
    Activations Density 0.000%

    No Known Activations