© 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. 13092
    Prev
    Next
    INDEX
    Explanations

    form-like input fields and submission-related words

    oai_token-act-pair · 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
     Monfieur
    -1.19
     tartalomajánló
    -1.16
     AssemblyCulture
    -1.09
     myſelf
    -1.08
     Efq
    -1.05
     autorytatywna
    -1.05
     Jefus
    -1.04
     Theſe
    -1.04
    ValueStyle
    -0.96
    RectangleBorder
    -0.96
    POSITIVE LOGITS
     
    0.55
    -
    0.54
     (
    0.47
    .
    0.45
     S
    0.44
     +
    0.43
     "
    0.42
     K
    0.41
    …
    0.40
     #
    0.40
    Activations Density 2.687%

    No Known Activations