© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132482
    Prev
    Next
    INDEX
    Explanations

    currency, slang, and specific terms

    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_1_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
    و
    1.67
    I
    1.43
    ש
    1.39
    다
    1.35
    ו
    1.13
    Z
    1.11
    Ic
    1.09
    드
    1.08
    ي
    1.07
    კ
    1.06
    POSITIVE LOGITS
    ре
    1.26
    ле
    1.26
    نین
    1.25
    ag
    1.23
    ai
    1.21
     لی
    1.19
     साथ
    1.17
     хода
    1.16
     други
    1.13
    اشی
    1.13
    Activations Density 0.000%

    No Known Activations