© 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. 11112
    Prev
    Next
    INDEX
    Explanations

    CSS code related to webkit appearance and slider thumbs with after/before pseudo-elements

    oai_token-act-pair · gemini-2.0-flash

    after/before

    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
     local
    -0.50
    IMPORTED
    -0.46
     prior
    -0.46
    Lời
    -0.46
     at
    -0.44
    atina
    -0.43
     willkommen
    -0.43
     unique
    -0.43
    وج
    -0.42
     completos
    -0.42
    POSITIVE LOGITS
    ंदीखरीदारी
    0.97
     Савезне
    0.92
     SwitchCompat
    0.87
     onPostExecute
    0.82
    BagConstraints
    0.81
     Efq
    0.79
    tableFuture
    0.77
     Monfieur
    0.77
     Rukh
    0.77
    enumi
    0.75
    Activations Density 3.805%

    No Known Activations