© 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. 12458
    Prev
    Next
    INDEX
    Explanations

    various forms of measurement and location

    oai_token-act-pair · gemini-2.0-flash

    distance measurement

    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
    AddTagHelper
    -0.68
    gyz
    -0.58
     monographs
    -0.50
     fractional
    -0.50
     hemsida
    -0.50
    macs
    -0.50
    mapbox
    -0.50
     élevées
    -0.50
    ROIT
    -0.49
     rå
    -0.49
    POSITIVE LOGITS
    Referencie
    0.76
     Thirty
    0.74
    Thirty
    0.71
     Meters
    0.69
     Twenty
    0.69
    Twenty
    0.69
    BeginContext
    0.69
     fifty
    0.69
     meter
    0.69
     Meter
    0.68
    Activations Density 1.324%

    No Known Activations