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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215503
    Prev
    Next
    INDEX
    Explanations

    shocking discovery, moment, secret, plot

    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
     I
    1.14
    IN
    1.05
    IG
    0.95
    OF
    0.93
    ri
    0.92
    ICK
    0.90
    tering
    0.89
    en
    0.89
    含ま
    0.88
    AY
    0.87
    POSITIVE LOGITS
    好
    1.33
    اں
    1.31
    ง
    1.24
    高
    1.23
    اً
    1.22
    است
    1.21
    از
    1.20
    位置
    1.19
    ก
    1.19
    ا
    1.18
    Activations Density 0.001%

    No Known Activations