© 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. 5101
    Prev
    Next
    INDEX
    Explanations

    strings of numbers that look like dates or version numbers

    oai_token-act-pair · gemini-2.0-flash

    code and technical information

    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
    :+:
    -0.46
     Bare
    -0.43
     feet
    -0.41
    Bare
    -0.41
    classnames
    -0.41
     $
    -0.40
     Kuh
    -0.40
     c
    -0.40
    resting
    -0.40
     Ast
    -0.39
    POSITIVE LOGITS
     ComVisible
    0.94
    featureID
    0.82
    StructEnd
    0.81
    IntoConstraints
    0.79
    
    0.76
    RetentionPolicy
    0.75
    SBATCH
    0.75
    LookAnd
    0.75
    хьтан
    0.75
    enumi
    0.73
    Activations Density 0.141%

    No Known Activations