© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235265
    Prev
    Next
    INDEX
    Explanations

    heard

    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_46_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
    权
    0.42
    ://"
    0.36
    權
    0.36
    குறித்து
    0.35
    કરણ
    0.35
     Poor
    0.34
    权的
    0.34
    ))}
    0.34
     poor
    0.33
     गरीब
    0.33
    POSITIVE LOGITS
     things
    0.58
     speculations
    0.51
    things
    0.50
     conjectures
    0.47
     suggestions
    0.46
    Things
    0.45
     coisas
    0.44
     것이
    0.42
     вещи
    0.42
     guesses
    0.41
    Activations Density 0.001%

    No Known Activations