© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260910
    Prev
    Next
    INDEX
    Explanations

    Jurong East, Rong

    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_5_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
     оско
    1.05
     немно
    1.05
    ן
    1.00
    リ
    0.98
     énon
    0.96
    ロッパ
    0.96
    াঃ
    0.91
    that
    0.89
    твы
    0.89
     êtres
    0.89
    POSITIVE LOGITS
    द
    1.27
    기
    1.25
    en
    1.23
     \
    1.23
    ii
    1.21
    of
    1.20
    <0x0D>
    1.16
    在
    1.16
     a
    1.15
    те
    1.15
    Activations Density 0.000%

    No Known Activations