© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172437
    Prev
    Next
    INDEX
    Explanations

    princesses and princes

    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_20_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
     ज
    0.35
     yielding
    0.34
     खाली
    0.33
     prit
    0.32
    хва
    0.32
    UNRELATED
    0.32
    aining
    0.32
     sprinting
    0.31
    陌
    0.31
    isas
    0.31
    POSITIVE LOGITS
    绊
    0.37
    Cel
    0.35
     mMediaPlayer
    0.34
    𝙿
    0.33
     Realt
    0.33
    Person
    0.33
     offices
    0.32
    伴
    0.32
     Biz
    0.32
    Red
    0.32
    Activations Density 0.000%

    No Known Activations