© 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. 90291
    Prev
    Next
    INDEX
    Explanations

    equal causation

    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
     l
    0.75
     sirve
    0.70
     index
    0.66
     isch
    0.65
     successivamente
    0.65
     field
    0.65
     size
    0.65
     vertical
    0.65
     nieuw
    0.64
     update
    0.64
    POSITIVE LOGITS
    čas
    0.64
    on
    0.59
    reacted
    0.58
    وم
    0.56
    Graphs
    0.56
    *
    0.55
    angered
    0.54
    }<\
    0.54
     vorgestellt
    0.53
     مطرح
    0.53
    Activations Density 0.001%

    No Known Activations