© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78235
    Prev
    Next
    INDEX
    Explanations

    poetry

    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_53_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
    ja
    0.75
    jen
    0.69
    ја
    0.68
    j
    0.66
    ј
    0.65
    jaw
    0.63
    jas
    0.61
    jai
    0.60
    jin
    0.59
    ję
    0.58
    POSITIVE LOGITS
    Sdk
    0.41
    зде
    0.39
     కని
    0.39
     Такая
    0.38
     গড়ে
    0.37
    ueil
    0.36
    AVER
    0.36
     Essentially
    0.36
    咔
    0.36
     io
    0.36
    Activations Density 0.013%

    No Known Activations