© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5885
    Prev
    Next
    INDEX
    Explanations

    statements of comparison and associations

    oai_token-act-pair · gemini-2.0-flash

    be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     esternos
    -0.54
     being
    -0.47
    past
    -0.45
    AsUp
    -0.44
     étant
    -0.43
     past
    -0.43
    da
    -0.42
    tic
    -0.42
    Spoljašnje
    -0.41
    @
    -0.41
    POSITIVE LOGITS
    verwijspagina
    0.73
    rrggbb
    0.66
    IUrlHelper
    0.66
    onViewCreated
    0.66
    awtextra
    0.66
    }$​
    0.65
    WireFormatLite
    0.65
    GroupLayout
    0.63
    SharedCtor
    0.63
     Monfieur
    0.63
    Activations Density 3.188%

    No Known Activations