© 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. 12697
    Prev
    Next
    INDEX
    Explanations

    words denoting quantities and limitations, and also some references.

    oai_token-act-pair · gemini-2.0-flash

    number

    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
     mucho
    -0.47
     viel
    -0.42
     much
    -0.41
    kegaard
    -0.39
    Much
    -0.39
     paljon
    -0.38
     mycket
    -0.38
    __))
    -0.38
     Much
    -0.37
    yczny
    -0.37
    POSITIVE LOGITS
     number
    3.06
    number
    2.70
     Number
    2.52
    Number
    2.47
     NUMBER
    2.33
     número
    2.30
     numbers
    2.14
    NUMBER
    2.11
     numero
    1.97
     num
    1.88
    Activations Density 6.120%

    No Known Activations