© 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
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 238788
    Prev
    Next
    INDEX
    Explanations

    describing things and places

    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_25_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
     Additionally
    0.46
    Additionally
    0.38
     ל
    0.38
    嗎
    0.38
    reetings
    0.37
     तभी
    0.37
     בנו
    0.37
     Boley
    0.37
     கூடுதலாக
    0.37
    步驟
    0.36
    POSITIVE LOGITS
     صارت
    0.41
     daya
    0.41
    ító
    0.40
    EMP
    0.39
    ₲
    0.38
    EMPT
    0.38
    UM
    0.38
    Dom
    0.38
     convertirse
    0.38
    UMN
    0.37
    Activations Density 0.001%

    No Known Activations