© 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. 232460
    Prev
    Next
    INDEX
    Explanations

    part of a phrase

    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
    ك
    0.84
     can
    0.73
    в
    0.66
     aé
    0.66
    л
    0.66
    ל
    0.64
     вас
    0.62
    та
    0.62
    ва
    0.57
    اً
    0.57
    POSITIVE LOGITS
    um
    0.72
     மட்டுமே
    0.65
    et
    0.63
    Α
    0.62
    r
    0.61
    ak
    0.59
    2
    0.57
     Adası
    0.57
    :
    0.57
    Tree
    0.56
    Activations Density 0.010%

    No Known Activations