© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12273
    Prev
    Next
    INDEX
    Explanations

    dates, objects, and quantities

    oai_token-act-pair · gemini-2.0-flash

    mechanical arrangements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     jegy
    -0.51
    Liên
    -0.50
    emark
    -0.50
     domestiques
    -0.49
    selbst
    -0.48
     getSub
    -0.48
     Selb
    -0.47
    getSub
    -0.47
    IDEN
    -0.47
     själv
    -0.46
    POSITIVE LOGITS
     protoimpl
    0.89
    SequentialGroup
    0.76
    AnchorStyles
    0.71
     Normdatei
    0.69
    FormTagHelper
    0.69
    \{\\
    0.69
     typelib
    0.69
     AssemblyTitle
    0.66
    TagMode
    0.66
    enumi
    0.63
    Activations Density 1.671%

    No Known Activations