© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181641
    Prev
    Next
    INDEX
    Explanations

    when, introduced, blocked, error

    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_29_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
     يُ
    0.39
     다니
    0.35
    したので
    0.35
    するので
    0.35
    oluene
    0.35
     Water
    0.34
     ಯ
    0.34
     राशन
    0.33
     জলের
    0.33
     Poll
    0.33
    POSITIVE LOGITS
    sided
    0.44
    २
    0.42
    Even
    0.42
    able
    0.42
     அதே
    0.41
    Evento
    0.41
    Country
    0.40
    Side
    0.40
    nungen
    0.40
    τει
    0.40
    Activations Density 0.001%

    No Known Activations