© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66777
    Prev
    Next
    INDEX
    Explanations

    codec and video compression

    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_41_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
     植物
    0.41
    カテゴ
    0.40
     категория
    0.38
     kategor
    0.38
    信用卡
    0.38
    㨁
    0.37
    罰
    0.37
     autoWatch
    0.37
    년간
    0.37
    غم
    0.37
    POSITIVE LOGITS
     codec
    1.57
    Codec
    1.45
     codecs
    1.44
    codec
    1.41
     coal
    1.11
    Coal
    0.94
    coal
    0.93
     Coal
    0.91
    煤
    0.90
     코
    0.87
    Activations Density 0.004%

    No Known Activations