© 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. 2185
    Prev
    Next
    INDEX
    Explanations

    terms used in graph theory

    oai_token-act-pair · gemini-2.0-flash

    directed graphs and cycles

    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
    achel
    -0.51
    inalg
    -0.49
    eternal
    -0.49
     Bundesrepublik
    -0.48
    coach
    -0.48
     WQS
    -0.47
     Amtrak
    -0.46
    skapet
    -0.46
    IBinder
    -0.46
    AddHtmlAttribute
    -0.44
    POSITIVE LOGITS
    +#+#
    0.65
     protoimpl
    0.64
    gonic
    0.62
    GEBURTSDATUM
    0.62
    dafx
    0.61
     ***!
    0.60
     Exacts
    0.60
    ScopeManager
    0.57
     depth
    0.56
    ymce
    0.56
    Activations Density 10.954%

    No Known Activations