© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151329
    Prev
    Next
    INDEX
    Explanations

    Corrective actions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     corrective
    1.92
     remedial
    1.86
     Remed
    1.35
     remediation
    0.95
     remedi
    0.54
     Rem
    0.41
     remed
    0.40
    聝
    0.38
    ellers
    0.36
     Blooming
    0.36
    POSITIVE LOGITS
    是
    0.75
     是
    0.73
     시
    0.64
     là
    0.61
     là
    0.55
     adalah
    0.52
    是一
    0.52
    都是
    0.47
     Là
    0.46
    Là
    0.46
    Activations Density 0.010%

    No Known Activations