© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163707
    Prev
    Next
    INDEX
    Explanations

    multilingual comparative words

    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_31_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
    骤
    0.41
    ={{
    0.40
     കാഴ്ച
    0.40
     Filosof
    0.39
    奋斗
    0.38
    を実行
    0.38
     Version
    0.37
    ށް
    0.37
    椹
    0.37
    Fil
    0.37
    POSITIVE LOGITS
    䍩
    0.41
     искусство
    0.39
     lowest
    0.39
     apertures
    0.37
    最低
    0.37
     negar
    0.37
     estimating
    0.36
    求める
    0.35
     outsource
    0.35
     slowest
    0.35
    Activations Density 0.000%

    No Known Activations