© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10255
    Prev
    Next
    INDEX
    Explanations

    the letter "B" preceded by the number "2"

    oai_token-act-pair · gemini-2.0-flash

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    writeFieldEnd
    -0.60
    difficult
    -0.57
     handleMessage
    -0.57
    Tembelea
    -0.56
    MENAFN
    -0.55
    ówczas
    -0.54
    évaluateur
    -0.54
    RenderAtEndOf
    -0.54
    npmjs
    -0.54
     difficult
    -0.53
    POSITIVE LOGITS
    OGND
    0.71
    AddHtmlAttribute
    0.69
    !("{
    0.61
    <bos>
    0.55
    protoimpl
    0.54
     @"/
    0.54
     <<<<<<<<<<<<<<
    0.54
    oredCriteria
    0.53
     onBind
    0.52
     consenti
    0.51
    Activations Density 1.093%

    No Known Activations