© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36023
    Prev
    Next
    INDEX
    Explanations

    biggest issue

    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_11_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
     be
    0.59
    <0xA8>
    0.58
     e
    0.57
     doctor
    0.57
     analyze
    0.54
    ครับ
    0.53
     inform
    0.52
     buyers
    0.52
     brah
    0.52
    ifica
    0.52
    POSITIVE LOGITS
    r
    0.84
    mRNA
    0.75
    p
    0.72
     Funcion
    0.71
     Même
    0.67
    o
    0.66
    g
    0.64
     Training
    0.64
    gène
    0.64
     навчання
    0.63
    Activations Density 0.022%

    No Known Activations