© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213949
    Prev
    Next
    INDEX
    Explanations

    substances

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    Iron
    0.91
     iron
    0.82
     Iron
    0.80
    鐵
    0.73
    铁
    0.69
    iron
    0.68
     आयरन
    0.67
    IRON
    0.66
     IRON
    0.65
    철
    0.64
    POSITIVE LOGITS
     fines
    0.44
     coca
    0.43
     elaborar
    0.43
     Coca
    0.40
     FLOR
    0.40
     Selector
    0.40
     ashes
    0.39
     dentures
    0.38
     අන
    0.37
     attacked
    0.37
    Activations Density 0.096%

    No Known Activations