© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140900
    Prev
    Next
    INDEX
    Explanations

    postdoctoral researcher or faculty roles

    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_12_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
    <h5>
    0.47
    {
    0.46
    私の
    0.42
    <0x0D>
    0.41
     परेशान
    0.41
    IM
    0.38
    IC
    0.38
    ように
    0.38
    我可以
    0.38
    </h5>
    0.37
    POSITIVE LOGITS
    u
    0.55
     Forza
    0.42
     toen
    0.41
    uoj
    0.41
    zył
    0.39
     piedi
    0.38
     sterilization
    0.38
    uze
    0.37
     cujo
    0.37
    uZ
    0.37
    Activations Density 0.000%

    No Known Activations