© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6133
    Prev
    Next
    INDEX
    Explanations

    method definitions in ruby code

    oai_token-act-pair · gemini-2.0-flash

    def

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.13
     def
    -0.94
    def
    -0.91
     Def
    -0.83
    Def
    -0.81
     Snow
    -0.73
    ########.
    -0.65
    Snow
    -0.63
     snow
    -0.59
    ⋱
    -0.58
    POSITIVE LOGITS
     surla
    0.61
    interopRequire
    0.56
     cherchés
    0.56
    μει
    0.56
     arras
    0.54
    서는
    0.54
     onOptions
    0.53
     soins
    0.52
     Neat
    0.52
    AddTagHelper
    0.51
    Activations Density 0.235%

    No Known Activations