© 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. 35048
    Prev
    Next
    INDEX
    Explanations

    was ist

    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
    á
    0.76
     היה
    0.71
    í
    0.70
    к
    0.70
    ле
    0.68
    ла
    0.65
    블릿
    0.65
    та
    0.63
     было
    0.62
    다
    0.62
    POSITIVE LOGITS
     not
    0.94
    about
    0.72
    t
    0.69
     about
    0.68
    <h3>
    0.65
    an
    0.64
    :
    0.64
    a
    0.64
     second
    0.63
     who
    0.62
    Activations Density 0.002%

    No Known Activations