© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139324
    Prev
    Next
    INDEX
    Explanations

    brands and stores

    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_12_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
    ნენ
    0.57
    є
    0.55
     γλώ
    0.53
     infiltrated
    0.52
    wolves
    0.52
    mnop
    0.51
     பிறகு
    0.51
    attiyam
    0.51
     развитие
    0.50
     öld
    0.50
    POSITIVE LOGITS
    h
    0.51
    就需要
    0.49
     {.
    0.49
    赉
    0.48
     TABLE
    0.47
     ওয়েবসাইট
    0.46
     Waver
    0.46
     baş
    0.46
     l
    0.45
     mandate
    0.45
    Activations Density 0.000%

    No Known Activations