© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216282
    Prev
    Next
    INDEX
    Explanations

    Summit

    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_47_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
     Hfn
    0.46
    రెడ్డి
    0.44
    עים
    0.40
    ప్తి
    0.39
    Lycodon
    0.38
    Ahmed
    0.38
     \|
    0.38
    HID
    0.38
     핵
    0.37
    Koh
    0.37
    POSITIVE LOGITS
    স্কার
    0.43
     bel
    0.38
    座
    0.38
    সারে
    0.38
    çando
    0.37
     деся
    0.35
    ber
    0.35
    ファ
    0.35
    çar
    0.35
    bert
    0.34
    Activations Density 0.000%

    No Known Activations