© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42052
    Prev
    Next
    INDEX
    Explanations

    how to make something easier

    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_22_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
     competing
    0.34
    epine
    0.33
    ttes
    0.32
    ptt
    0.31
    űr
    0.31
    ott
    0.31
     margen
    0.30
    ﺮ
    0.30
    アレ
    0.30
    ppi
    0.30
    POSITIVE LOGITS
     легко
    0.49
     easily
    0.48
     facilement
    0.46
     kolay
    0.44
     fácil
    0.44
     आसानी
    0.44
    簡単に
    0.44
     dễ
    0.43
     fáciles
    0.43
    easily
    0.43
    Activations Density 0.049%

    No Known Activations