© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129604
    Prev
    Next
    INDEX
    Explanations

    ju

    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_1_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
    :
    1.51
     I
    1.17
    <0x91>
    1.16
    dale
    1.16
    dj
    1.13
    dik
    1.09
    <0xB8>
    1.07
    ная
    1.05
    í
    1.05
    din
    1.05
    POSITIVE LOGITS
    その
    1.55
    ע
    1.55
    ع
    1.51
    この
    1.44
    ل
    1.36
    や
    1.30
    K
    1.29
    $\
    1.27
    ために
    1.23
    もちろん
    1.22
    Activations Density 0.001%

    No Known Activations