© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195635
    Prev
    Next
    INDEX
    Explanations

    Swo, spo, or similar sounds

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ску
    0.47
    ஸ்க
    0.45
    сками
    0.43
    \}$.
    0.42
    ស្ស
    0.41
    સ
    0.40
    স
    0.40
    ەس
    0.40
    ⵙ
    0.40
    æss
    0.39
    POSITIVE LOGITS
    ло
    0.44
    лло
    0.39
    ্ল
    0.39
     adi
    0.38
    クリ
    0.38
     Mord
    0.38
    ad
    0.38
    кри
    0.38
    лович
    0.38
    邰
    0.37
    Activations Density 0.000%

    No Known Activations