© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107840
    Prev
    Next
    INDEX
    Explanations

    ability to

    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_2_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
     can
    1.06
     on
    1.00
    する
    0.99
    ر
    0.99
    $.
    0.91
     titrated
    0.88
     the
    0.88
    th
    0.86
    ために
    0.84
     has
    0.83
    POSITIVE LOGITS
    i
    1.30
    p
    1.16
    y
    1.15
    it
    1.01
    ET
    0.91
     siguiente
    0.91
     gebru
    0.89
     vem
    0.87
     functie
    0.86
     privind
    0.86
    Activations Density 0.002%

    No Known Activations