© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 208519
    Prev
    Next
    INDEX
    Explanations

    Wildlife and conservation agencies

    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_19_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
     втра
    0.50
    -¹
    0.42
     izgub
    0.42
     traffickers
    0.42
     trafficking
    0.41
     diastolic
    0.41
    ിട
    0.41
     gubit
    0.41
    uš
    0.40
     polymorphisms
    0.40
    POSITIVE LOGITS
    URES
    0.43
    जारी
    0.42
     şart
    0.41
    ருங்கள்
    0.41
    cupine
    0.40
    त्रे
    0.40
    斎
    0.40
    áles
    0.39
    äle
    0.39
     determ
    0.39
    Activations Density 0.000%

    No Known Activations