© 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. 39895
    Prev
    Next
    INDEX
    Explanations

    Changi Airport

    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
     t
    0.65
     bolster
    0.65
     bare
    0.63
     bosh
    0.63
     bolstering
    0.61
     manfaat
    0.60
     outpost
    0.59
     dura
    0.58
     stvar
    0.58
     Aad
    0.58
    POSITIVE LOGITS
    name
    0.64
    and
    0.63
    ک
    0.63
    ーム
    0.63
    ام
    0.59
    im
    0.58
    that
    0.57
    called
    0.57
    certified
    0.56
    even
    0.55
    Activations Density 0.000%

    No Known Activations