© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60452
    Prev
    Next
    INDEX
    Explanations

    air, aire, respiration

    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
    6
    0.60
    chester
    0.57
    chtigen
    0.54
    cadherin
    0.54
    aks
    0.53
    șit
    0.53
    ated
    0.52
    5
    0.52
    ci
    0.51
    collective
    0.51
    POSITIVE LOGITS
     які
    0.59
     naf
    0.57
     때는
    0.55
    то
    0.55
     padre
    0.54
     対象
    0.54
    ির
    0.53
     rápido
    0.53
     библиоте
    0.53
     мое
    0.53
    Activations Density 0.006%

    No Known Activations