© 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. 161747
    Prev
    Next
    INDEX
    Explanations

    analogy reasoning or formula completion

    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
     हेयर
    0.35
     rispetto
    0.34
    ችን
    0.34
     circost
    0.34
    檀
    0.33
     rye
    0.33
     thưởng
    0.33
    啻
    0.33
     নি
    0.32
     ধান
    0.32
    POSITIVE LOGITS
     Participation
    0.44
    ēm
    0.42
    గొ
    0.40
     छुटकारा
    0.40
     participation
    0.39
    روف
    0.38
    слан
    0.38
    撻
    0.38
    слав
    0.38
    Ⲉ
    0.37
    Activations Density 0.001%

    No Known Activations