© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7092
    Prev
    Next
    INDEX
    Explanations

    the German words "Brief," "muss," "hätte," and "geschrieben," and the English phrase "can be."

    oai_token-act-pair · gemini-2.0-flash

    be

    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
    Negative Logits
     be
    -1.58
     was
    -1.45
     être
    -1.33
     been
    -1.30
     essere
    -1.27
     being
    -1.24
     být
    -1.16
     быть
    -1.15
    Was
    -1.12
     Was
    -1.09
    POSITIVE LOGITS
    ThroughAttribute
    0.67
     Insee
    0.58
    HostException
    0.57
    BASEPATH
    0.57
    openSession
    0.54
     Sloveniji
    0.51
    lgari
    0.49
    省市镇
    0.49
    principalColumn
    0.48
    writeFieldEnd
    0.48
    Activations Density 0.663%

    No Known Activations