© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149181
    Prev
    Next
    INDEX
    Explanations

    sinusoidal encodings

    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_23_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
     diff
    0.46
     dominions
    0.42
    ifferent
    0.41
    ᔕ
    0.41
     পূ
    0.41
    蒉
    0.41
     challenging
    0.39
    °;
    0.39
     AMO
    0.39
     asympt
    0.38
    POSITIVE LOGITS
    рок
    0.46
    ak
    0.44
    נג
    0.43
    늑
    0.42
    Authenticated
    0.42
    System
    0.42
    システム
    0.41
    Didn
    0.40
    消息
    0.40
    ድን
    0.40
    Activations Density 0.000%

    No Known Activations