© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13805
    Prev
    Next
    INDEX
    Explanations

    articles that contain academic research and supporting information

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     a
    -0.77
     the
    -0.75
     
    -0.74
     (
    -0.68
     I
    -0.64
     and
    -0.60
     B
    -0.60
     is
    -0.59
     an
    -0.59
    .
    -0.59
    POSITIVE LOGITS
     Efq
    1.50
    ſelves
    1.45
     Majefty
    1.42
     pleaſure
    1.41
    AndEndTag
    1.37
     Chriftian
    1.34
     greateſt
    1.32
     Reſ
    1.32
     Italijanski
    1.31
     Anſ
    1.30
    Activations Density 5.192%

    No Known Activations