© 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. 32370
    Prev
    Next
    INDEX
    Explanations

    approximately or around

    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
    嶉
    0.36
    ผิด
    0.33
    滝
    0.32
    сным
    0.32
    ोटी
    0.32
    quoted
    0.32
    ্যেষ্ঠ
    0.31
    昦
    0.31
     vacanam
    0.31
     tonnage
    0.31
    POSITIVE LOGITS
    1
    0.43
    5
    0.41
    3
    0.41
    4
    0.40
    6
    0.39
    7
    0.39
    apiro
    0.38
     ধারনা
    0.37
    0.37
    <unused100>
    0.37
    Activations Density 0.126%

    No Known Activations