© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127354
    Prev
    Next
    INDEX
    Explanations

    amyloidosis, amydala

    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_3_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
    ;
    0.79
    ר
    0.76
    р
    0.75
    б
    0.71
     compuestos
    0.70
    .
    0.69
    বিভিন্ন
    0.66
    ::
    0.66
    ಸ್ಕೊ
    0.66
    ф
    0.66
    POSITIVE LOGITS
     it
    0.70
    ين
    0.64
    man
    0.62
    ete
    0.59
    IN
    0.57
    jection
    0.57
    os
    0.57
    me
    0.57
    urd
    0.56
    ali
    0.55
    Activations Density 0.000%

    No Known Activations