© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14278
    Prev
    Next
    INDEX
    Explanations

    answers to ultimate questions

    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_13_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
    .'”
    0.49
     അദ്ദേഹം
    0.49
    judul
    0.47
     विवाद
    0.44
     praised
    0.43
     tulis
    0.43
    냔
    0.43
    unächst
    0.42
    anfaatkan
    0.42
     написано
    0.41
    POSITIVE LOGITS
    arro
    0.42
    r
    0.38
    се
    0.37
     indole
    0.37
    سكري
    0.36
     glycine
    0.35
     Glucose
    0.35
     sickly
    0.34
    that
    0.34
    Will
    0.33
    Activations Density 0.001%

    No Known Activations