© 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. 10832
    Prev
    Next
    INDEX
    Explanations

    the number zero, especially within a version number

    oai_token-act-pair · gemini-2.0-flash

    0

    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
    ANTON
    -0.50
    一郎
    -0.47
    Datuak
    -0.47
    ↵↵
    -0.47
    ALSO
    -0.46
    PhysRevLett
    -0.45
     Aguirre
    -0.45
    atars
    -0.44
    טל
    -0.44
     #
    -0.43
    POSITIVE LOGITS
     ExecuteAsync
    0.93
     TextAppearance
    0.81
    PerformLayout
    0.80
     onCreateView
    0.68
    IsContent
    0.67
     cherchés
    0.66
    OGND
    0.66
     متعلقه
    0.66
     meille
    0.65
     كومونز
    0.65
    Activations Density 0.252%

    No Known Activations