© 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. 52880
    Prev
    Next
    INDEX
    Explanations

    to desire or want

    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
    empirical
    0.40
     skill
    0.40
     मह
    0.39
    &
    0.39
    "."
    0.37
     Skill
    0.37
     uneven
    0.37
    Skill
    0.37
    skill
    0.36
    ደን
    0.36
    POSITIVE LOGITS
     desire
    0.63
     желание
    0.62
     хочется
    0.57
     appetite
    0.50
     deseo
    0.50
     appet
    0.50
     inspires
    0.48
     desejo
    0.48
    懶
    0.47
     WANT
    0.46
    Activations Density 0.071%

    No Known Activations