© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44914
    Prev
    Next
    INDEX
    Explanations

    pygame.init()

    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
     la
    0.66
     de
    0.65
     entre
    0.64
    خدام
    0.63
    </li>
    0.62
    </h3>
    0.61
     en
    0.60
    عام
    0.59
    </h6>
    0.58
     compassion
    0.57
    POSITIVE LOGITS
    ка
    0.83
     hạ
    0.69
    ংকার
    0.67
     Admiralty
    0.66
    т
    0.66
    ン
    0.65
     एग्रीकल्चर
    0.64
     пунктов
    0.64
    ва
    0.63
    गड
    0.63
    Activations Density 0.000%

    No Known Activations