© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14194
    Prev
    Next
    INDEX
    Explanations

    numbers

    oai_token-act-pair · gemini-2.0-flash

    Scientific and technical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    enumi
    -0.51
    ########.
    -0.45
    Vec
    -0.42
    Portale
    -0.42
    UEL
    -0.41
    ls
    -0.41
     atas
    -0.40
    ysio
    -0.40
     لاس
    -0.40
    processData
    -0.40
    POSITIVE LOGITS
    ^(@)
    0.73
     Италијани
    0.69
     Audiodateien
    0.66
    parsedMessage
    0.65
     CMM
    0.63
     MM
    0.62
     foot
    0.60
    Mm
    0.59
     يتيمه
    0.59
    MMV
    0.59
    Activations Density 6.778%

    No Known Activations