© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12516
    Prev
    Next
    INDEX
    Explanations

    terms related to data analysis and studies

    oai_token-act-pair · gemini-2.0-flash

    analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     analysis
    -2.53
     Analysis
    -2.39
     ANALYSIS
    -2.27
    analysis
    -2.27
    Analysis
    -2.25
     analyses
    -2.16
    ANALYSIS
    -2.06
     analyzed
    -2.03
     Analyses
    -2.03
     analysed
    -2.02
    POSITIVE LOGITS
     Ат
    0.52
     OFDb
    0.50
     cré
    0.50
    ús
    0.46
    çeği
    0.46
    sione
    0.45
    idov
    0.45
    ASI
    0.45
    RegressionTest
    0.45
    hef
    0.44
    Activations Density 4.109%

    No Known Activations