© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206535
    Prev
    Next
    INDEX
    Explanations

    savings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    +|\
    0.39
    完美
    0.37
    மில்
    0.37
     веществ
    0.37
     RULES
    0.37
     hybridization
    0.36
     under
    0.36
     ABS
    0.35
    -”
    0.35
    UnderTest
    0.35
    POSITIVE LOGITS
     due
    0.74
     Due
    0.68
    due
    0.65
    Due
    0.62
     devido
    0.57
     بسبب
    0.54
     debido
    0.53
    由于
    0.52
     由于
    0.48
     DUE
    0.48
    Activations Density 0.002%

    No Known Activations