© 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
    2. Gemma-3-27B-IT
    3. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 194016
    Prev
    Next
    INDEX
    Explanations

    math word problems

    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_27_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
    헹
    0.40
     없
    0.40
     chalc
    0.40
     চাওয়া
    0.40
     跟
    0.39
     張
    0.39
     Ook
    0.39
    ﹣
    0.39
     količ
    0.39
     soglas
    0.38
    POSITIVE LOGITS
    /}
    0.39
    手指
    0.38
    操作
    0.38
    жными
    0.37
    ضرب
    0.37
    ('../
    0.36
    Html
    0.36
    Spiel
    0.35
    投注
    0.35
    players
    0.34
    Activations Density 0.002%

    No Known Activations