© 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. 51822
    Prev
    Next
    INDEX
    Explanations

    programming symbols and special characters

    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
     يستخدم
    0.38
    ẹt
    0.38
    レット
    0.38
     SUPPL
    0.37
     sunflowers
    0.36
     matériel
    0.36
    を提供する
    0.36
    撵
    0.36
    reflectionCamera
    0.36
     advertisement
    0.35
    POSITIVE LOGITS
     Lif
    0.42
    Lif
    0.41
     para
    0.39
    para
    0.38
     praw
    0.38
    lif
    0.37
     pw
    0.36
     Municipal
    0.36
    sem
    0.35
    ほ
    0.34
    Activations Density 0.001%

    No Known Activations