© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11405
    Prev
    Next
    INDEX
    Explanations

    code and licensing information

    oai_token-act-pair · gemini-2.0-flash

    Code and software licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     avoient
    -0.75
    AndEndTag
    -0.71
     OBITUARY
    -0.67
    DoubleQuotes
    -0.67
     étoient
    -0.65
     auroit
    -0.64
     quelcon
    -0.64
    rizona
    -0.63
     enfans
    -0.62
     ſein
    -0.62
    POSITIVE LOGITS
    "]
    0.54
    contentLoaded
    0.54
    argout
    0.53
    Enllaços
    0.53
    ++
    0.53
    "):
    0.52
     समीक्षाओं
    0.51
    CloseOperation
    0.51
     and
    0.49
    "])
    0.48
    Activations Density 13.734%

    No Known Activations