© 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. 61851
    Prev
    Next
    INDEX
    Explanations

    Latin imperatives

    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
    л
    0.66
     અથવા
    0.65
     tradizione
    0.61
     அல்லது
    0.59
     பொதுவாக
    0.59
    ığı
    0.59
     pegatina
    0.57
     ಅಥವಾ
    0.57
     tradición
    0.57
     tradiciones
    0.55
    POSITIVE LOGITS
    fares
    0.45
    barang
    0.45
    a
    0.44
    pes
    0.43
    bo
    0.43
    South
    0.42
     parsed
    0.42
     I
    0.42
    pan
    0.41
    bolts
    0.41
    Activations Density 0.000%

    No Known Activations