© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126181
    Prev
    Next
    INDEX
    Explanations

    horse anatomy and breeds

    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
     Ayn
    0.52
     AIA
    0.42
    溉
    0.40
     integrator
    0.39
     Atlas
    0.39
    BDA
    0.39
     rationally
    0.39
    麓
    0.39
    ೈ
    0.38
     Aydın
    0.37
    POSITIVE LOGITS
     annoyance
    0.42
    Change
    0.38
    createText
    0.35
     inconven
    0.34
     نقص
    0.34
    Test
    0.34
    বিষ্য
    0.34
     trom
    0.34
    onDidChange
    0.33
    Instructions
    0.33
    Activations Density 0.004%

    No Known Activations