© 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. 10273
    Prev
    Next
    INDEX
    Explanations

    hips and pelvis anatomy

    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
    k
    0.54
    be
    0.54
    のない
    0.52
    ab
    0.51
    me
    0.51
     배워
    0.49
    op
    0.49
    laser
    0.49
    ik
    0.48
    ree
    0.47
    POSITIVE LOGITS
     divulg
    0.55
    Idioma
    0.55
     Kait
    0.55
     coerc
    0.55
     cálculo
    0.53
    Número
    0.52
    <0x8C>
    0.52
     disg
    0.51
    É
    0.51
    ᱹ
    0.51
    Activations Density 0.033%

    No Known Activations