© 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. 36711
    Prev
    Next
    INDEX
    Explanations

    oceanography and salinity

    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
    dni
    0.52
    ables
    0.50
    asers
    0.50
    p
    0.49
     baked
    0.47
    ters
    0.46
     nont
    0.45
     necro
    0.45
     cuento
    0.45
    ㅍ
    0.45
    POSITIVE LOGITS
     Navy
    0.61
     Zijn
    0.61
     Undang
    0.58
    ној
    0.57
     Sekarang
    0.56
    海洋
    0.56
     оке
    0.55
     с
    0.54
    妷
    0.53
    стях
    0.53
    Activations Density 0.022%

    No Known Activations