© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204184
    Prev
    Next
    INDEX
    Explanations

    ships disappearing hull first

    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_37_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
     larva
    0.40
     손
    0.39
     Occupational
    0.39
    
    0.39
    糠
    0.38
    EDED
    0.38
     đu
    0.38
     कर्मी
    0.38
    惟
    0.38
    隨
    0.37
    POSITIVE LOGITS
    ட்ர
    0.40
    dard
    0.37
    ädchen
    0.37
     lensing
    0.35
    reliance
    0.35
    chev
    0.35
    സ്റ്റ
    0.35
    യാണ
    0.34
     Daya
    0.34
    )].
    0.34
    Activations Density 0.001%

    No Known Activations