© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162218
    Prev
    Next
    INDEX
    Explanations

    AI content detectors

    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_31_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
    evoluzione
    0.24
    Evolution
    0.23
    коли
    0.22
    evolution
    0.22
    tired
    0.22
    uckle
    0.21
    editing
    0.21
    诱
    0.21
     allow
    0.21
     unfolding
    0.21
    POSITIVE LOGITS
    oban
    0.22
    වත
    0.22
    cityName
    0.22
     неу
    0.22
    ,=
    0.22
     Sheet
    0.21
     oficio
    0.21
     শিক্ষার্থীর
    0.21
     खराब
    0.21
     വിദ്യാഭ്യാസ
    0.21
    Activations Density 0.006%

    No Known Activations