© 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. 7517
    Prev
    Next
    INDEX
    Explanations

    text describing the construction, maintenance, and condition of roads, rails, and related infrastructure

    oai_token-act-pair · gemini-2.0-flash

    highways and roads

    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
    PyExc
    -0.47
     Popo
    -0.46
    aster
    -0.44
    ()")
    -0.44
    SharedCtor
    -0.43
    findpost
    -0.42
     "..\..\
    -0.41
    igt
    -0.41
    asters
    -0.41
     ro
    -0.40
    POSITIVE LOGITS
    RectangleBorder
    0.85
    ConstraintMaker
    0.76
     transfieras
    0.73
    MemoryWarning
    0.69
     Administrativna
    0.69
    SequentialGroup
    0.66
    DeleteBehavior
    0.66
     transférez
    0.65
     للمعارف
    0.65
    WithIOException
    0.63
    Activations Density 2.029%

    No Known Activations