© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75676
    Prev
    Next
    INDEX
    Explanations

    my + endearment

    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_31_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
    ufen
    0.37
    LIS
    0.35
    Kung
    0.34
    Cult
    0.34
    bern
    0.34
     fēng
    0.33
     lej
    0.33
    {}
    0.33
    Prz
    0.32
    icca
    0.32
    POSITIVE LOGITS
     enchantment
    0.44
     goalie
    0.43
    的他
    0.40
     impasse
    0.38
     boys
    0.38
     memoranda
    0.38
     puppy
    0.38
     anthocyan
    0.38
     slats
    0.38
     mite
    0.38
    Activations Density 0.014%

    No Known Activations