© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206612
    Prev
    Next
    INDEX
    Explanations

    essential

    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_19_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
     CBC
    0.44
     중요
    0.43
     wichtigen
    0.42
     illeg
    0.42
     ঘটনা
    0.41
     истины
    0.41
    Questions
    0.40
     Ι
    0.40
     ideals
    0.40
    Priority
    0.40
    POSITIVE LOGITS
    yin
    0.42
     médico
    0.41
     कहलाता
    0.39
    liability
    0.39
     recuer
    0.39
     ઉત્પાદ
    0.38
     उत्पाद
    0.38
     funzione
    0.38
    atoon
    0.37
    స్క
    0.37
    Activations Density 0.014%

    No Known Activations