© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201856
    Prev
    Next
    INDEX
    Explanations

    grazing animals

    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_37_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
     refuge
    0.90
    逃
    0.84
     fled
    0.80
     asylum
    0.72
     escaped
    0.71
     refug
    0.70
     Refuge
    0.69
     fleeing
    0.69
    escape
    0.68
     escape
    0.67
    POSITIVE LOGITS
     Gra
    0.42
    nms
    0.42
    Gra
    0.41
    俘
    0.41
     prisoner
    0.40
     Arrest
    0.40
     grazing
    0.40
     captivity
    0.38
     அரை
    0.38
     Litter
    0.37
    Activations Density 0.010%

    No Known Activations