© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4298
    Prev
    Next
    INDEX
    Explanations

    words and short phrases in the middle of sentences or offset with a space, tab, or punctuation, possibly identifying transitions or time-related events

    oai_token-act-pair · gemini-2.0-flash

    were

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     utafitiHapana
    -0.99
    UrlResolution
    -0.84
    abestanden
    -0.81
     '\\;'
    -0.79
    AsUp
    -0.73
     Superhosts
    -0.72
     okuyayım
    -0.71
    béco
    -0.71
     الحره
    -0.70
    RegressionTest
    -0.70
    POSITIVE LOGITS
    кульп
    0.41
     scom
    0.37
    })+\
    0.37
    Scroller
    0.36
    UDA
    0.36
    фор
    0.36
     искать
    0.35
    דר
    0.35
     созда
    0.35
    leu
    0.35
    Activations Density 0.918%

    No Known Activations