© 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. 11073
    Prev
    Next
    INDEX
    Explanations

    HTML or XML code

    oai_token-act-pair · gemini-2.0-flash

    HTML tags

    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
    amp
    -1.05
    quot
    -0.94
    nbsp
    -0.81
     amp
    -0.81
     Amp
    -0.75
    ldquo
    -0.66
    Amp
    -0.65
    gt
    -0.57
    AMP
    -0.54
     amplifiers
    -0.54
    POSITIVE LOGITS
    abestanden
    1.09
    SourceChecksum
    1.05
    GEBURTSDATUM
    1.02
     propOrder
    1.01
    Geplaatst
    1.01
    帖最后由
    1.00
    expandindo
    0.96
    StructEnd
    0.96
    ⓧ
    0.95
    ]")]
    0.93
    Activations Density 2.144%

    No Known Activations