© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64479
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     dzień
    0.42
    쁜
    0.41
    ✲
    0.41
     немного
    0.36
    沥
    0.36
    ственном
    0.35
    あす楽
    0.35
    幫
    0.35
     Tecn
    0.34
    電機
    0.34
    POSITIVE LOGITS
     ইস্ট
    0.43
     One
    0.42
    One
    0.41
     別
    0.40
    она
    0.40
    ɥ
    0.38
     കീ
    0.37
    বর্তী
    0.36
     quantized
    0.36
    oot
    0.36
    Activations Density 0.001%

    No Known Activations