© 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. 3044
    Prev
    Next
    INDEX
    Explanations

    words or phrases common in scientific or technical papers

    oai_token-act-pair · gemini-2.0-flash

    scientific methods and approaches

    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
     Theſe
    -0.75
     becauſe
    -0.74
     chofe
    -0.73
     myſelf
    -0.73
     uſed
    -0.71
     Anſ
    -0.69
     ſeveral
    -0.69
     purpoſe
    -0.69
     raiſ
    -0.69
     againſt
    -0.69
    POSITIVE LOGITS
    \{\\
    0.56
    Rozm
    0.47
     leads
    0.45
     deals
    0.45
    naturally
    0.44
    helfen
    0.42
     Re
    0.42
     sacrifices
    0.42
    sacrifice
    0.42
     
    0.41
    Activations Density 8.890%

    No Known Activations