© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56607
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    áciu
    0.51
    น้อย
    0.49
    ί
    0.47
    δό
    0.45
     l
    0.45
    ны
    0.44
    น
    0.43
    ল
    0.42
    en
    0.41
    ácia
    0.40
    POSITIVE LOGITS
    कभी
    0.50
    בש
    0.49
     драй
    0.49
     ljub
    0.48
    .'/
    0.47
     berbagai
    0.46
     süt
    0.46
    ཙ
    0.46
     çeşitli
    0.46
    各种
    0.46
    Activations Density 0.000%

    No Known Activations