© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159223
    Prev
    Next
    INDEX
    Explanations

    largely

    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_2_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
    de
    1.88
    t
    1.87
    st
    1.52
    th
    1.48
    i
    1.47
    c
    1.44
    n
    1.34
    da
    1.34
    le
    1.27
    z
    1.26
    POSITIVE LOGITS
    ला
    1.49
     can
    1.30
    на
    1.25
     τα
    1.22
     direta
    1.18
    بی
    1.16
     pourra
    1.13
     buvo
    1.12
    อยาก
    1.12
    ง
    1.11
    Activations Density 0.003%

    No Known Activations