© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12776
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence delimiters, with some sensitivity to sentence beginnings and possible slight bias toward content related to fictional works.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     since
    -0.60
     auto
    -0.55
     despite
    -0.54
     the
    -0.51
    reu
    -0.50
     much
    -0.50
     to
    -0.49
     language
    -0.49
     ch
    -0.49
    AnchorStyles
    -0.49
    POSITIVE LOGITS
     rospy
    0.72
     Jefus
    0.69
    AsUp
    0.69
     Efq
    0.65
     Chrift
    0.65
    felves
    0.64
    expandindo
    0.62
     itſelf
    0.61
    loroethene
    0.60
    IContainer
    0.59
    Activations Density 2.174%

    No Known Activations