© 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. 123200
    Prev
    Next
    INDEX
    Explanations

    professional closing regards

    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
    ↵
    0.74
     divulg
    0.74
     λ
    0.64
     leis
    0.64
    <0xA0>
    0.62
    -
    0.60
     pone
    0.60
     demost
    0.59
    ↵↵
    0.58
    ва
    0.57
    POSITIVE LOGITS
    Basis
    0.70
    Пре
    0.68
     Kỳ
    0.68
    Лу
    0.68
    Три
    0.68
     Хоро
    0.66
    Зак
    0.66
    Dihydro
    0.66
    Гор
    0.65
    Characteristic
    0.64
    Activations Density 0.002%

    No Known Activations