© 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. 89370
    Prev
    Next
    INDEX
    Explanations

    molds

    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
     mesurer
    0.36
     측정
    0.36
     তুল
    0.35
     б
    0.35
     travers
    0.34
     ท
    0.34
     मापने
    0.34
     يُ
    0.33
     অ্যাল
    0.33
    تاز
    0.33
    POSITIVE LOGITS
    䪱
    0.42
    RxDocument
    0.42
    我觉得
    0.41
     komen
    0.41
     heli
    0.41
     चाहते
    0.41
     આવે
    0.39
     perquè
    0.39
     आए
    0.39
    豈
    0.39
    Activations Density 0.036%

    No Known Activations