© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16727
    Prev
    Next
    INDEX
    Explanations

    Lists with numbered or bulleted items

    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_34_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
    ending
    0.40
     ending
    0.38
    ŷ
    0.38
    Ending
    0.37
     endings
    0.36
    atuan
    0.36
    erts
    0.34
     Ending
    0.34
    "]:
    0.33
     banning
    0.33
    POSITIVE LOGITS
    AddToCart
    0.41
    ليه
    0.38
    عى
    0.38
     살펴보
    0.38
    しております
    0.37
     ниво
    0.37
    mektedir
    0.35
     περισ
    0.35
     rhod
    0.35
    actos
    0.35
    Activations Density 0.014%

    No Known Activations