© 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. 162957
    Prev
    Next
    INDEX
    Explanations

    blood cells and physiology

    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
     deaf
    0.49
    聾
    0.46
    ESI
    0.41
     Ears
    0.40
     deafness
    0.38
    👂
    0.38
     dine
    0.38
    epub
    0.37
     Deaf
    0.37
    Sound
    0.36
    POSITIVE LOGITS
     Collins
    0.38
     discourse
    0.38
     intercepts
    0.36
     Downt
    0.36
     Malt
    0.36
     (**
    0.36
     hoá
    0.36
    旃
    0.36
     அர
    0.35
     Discourse
    0.35
    Activations Density 0.012%

    No Known Activations