© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12980
    Prev
    Next
    INDEX
    Explanations

    code excerpts from system logs or configuration examples.

    oai_token-act-pair · gemini-2.0-flash

    say slash or quote

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ichtigung
    -0.55
    DeleteBehavior
    -0.53
    
    -0.50
     unto
    -0.47
    ^(@)
    -0.46
     
    -0.45
    ?」
    -0.44
      (
    -0.44
    principalColumn
    -0.44
    %";
    -0.44
    POSITIVE LOGITS
     /
    2.42
     $/
    1.42
     /$
    1.41
     /(
    1.35
    ／
    1.33
     /.
    1.30
     "/
    1.26
     /-
    1.24
     '/
    1.23
     /\
    1.23
    Activations Density 9.294%

    No Known Activations