© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4966
    Prev
    Next
    INDEX
    Explanations

    guardrails

    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_39_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
     mocked
    0.39
     mocking
    0.38
    লেম
    0.36
     unim
    0.35
    cooler
    0.35
    eeq
    0.35
    怯
    0.35
    翮
    0.35
     cosmic
    0.34
    ลาส
    0.34
    POSITIVE LOGITS
    ジン
    0.41
    dihydroxy
    0.39
    依托
    0.38
    值得
    0.37
    NewGuid
    0.37
     შემთხვევ
    0.36
    ificante
    0.35
    ピンク
    0.35
    tier
    0.35
    fibre
    0.35
    Activations Density 0.048%

    No Known Activations