© 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. 89501
    Prev
    Next
    INDEX
    Explanations

    available / доступен

    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
    Basis
    0.57
    Leaf
    0.55
    Fert
    0.52
    A
    0.52
     spoiled
    0.52
    Pear
    0.51
    O
    0.51
    Metal
    0.50
    Man
    0.50
    Road
    0.49
    POSITIVE LOGITS
     télévision
    0.60
     investigación
    0.59
     biết
    0.59
     oficina
    0.58
     escritório
    0.58
    驊
    0.57
     hoặc
    0.57
     büyü
    0.57
     acordo
    0.56
    ждает
    0.55
    Activations Density 0.001%

    No Known Activations