© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66349
    Prev
    Next
    INDEX
    Explanations

    convenience stores

    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_41_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
    baseline
    0.42
     fusible
    0.39
     Maternity
    0.37
     deuterium
    0.37
     Ort
    0.37
    affer
    0.36
    cribable
    0.36
    肾
    0.35
    Baseline
    0.35
     Saskatoon
    0.35
    POSITIVE LOGITS
     convenience
    1.88
     Convenience
    1.77
    便利
    1.51
    Conven
    1.49
     conven
    1.39
    conven
    1.36
     편
    1.25
     Conven
    1.23
     convenient
    1.19
     conveniences
    1.19
    Activations Density 0.002%

    No Known Activations