© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32616
    Prev
    Next
    INDEX
    Explanations

    location names and measurements

    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_31_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
     testify
    0.39
    🤍
    0.39
     sweetened
    0.36
     stabilized
    0.36
     उठ
    0.35
     వ్య
    0.35
    qb
    0.35
    ეთ
    0.34
     happily
    0.34
    textArea
    0.33
    POSITIVE LOGITS
    как
    0.42
    如
    0.39
    inca
    0.38
    ⚋
    0.38
    ByAppending
    0.38
    ική
    0.37
    Latin
    0.37
    ভব
    0.37
    Hlav
    0.37
     как
    0.36
    Activations Density 0.000%

    No Known Activations