© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1984
    Prev
    Next
    INDEX
    Explanations

    mentions of "chi" and "hope"

    oai_token-act-pair · gemini-2.0-flash

    Chi-square tests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    setVerticalGroup
    -0.72
    __":
    -0.66
    EndGlobalSection
    -0.66
     Theſe
    -0.62
     myſelf
    -0.60
     AssemblyVersion
    -0.58
     Vim
    -0.57
     Jefus
    -0.56
     comigo
    -0.56
     Cuth
    -0.56
    POSITIVE LOGITS
    ValueGenerated
    0.50
    |_{\
    0.47
     TestBed
    0.45
    ValueStyle
    0.42
    rungsseite
    0.41
    इड
    0.40
    TryParse
    0.39
     part
    0.38
    quote
    0.38
    #
    0.38
    Activations Density 0.584%

    No Known Activations