© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11895
    Prev
    Next
    INDEX
    Explanations

    HTML code fragments, especially tags and attributes like "href", "title", "class", and "span"

    oai_token-act-pair · gemini-2.0-flash

    HTML class/style code

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.98
     Theſe
    -0.83
     disambiguazione
    -0.75
     Anſ
    -0.73
    expandindo
    -0.70
     whoſe
    -0.70
     reaſon
    -0.68
    ſelves
    -0.68
     auffi
    -0.68
     Beſ
    -0.68
    POSITIVE LOGITS
     =
    1.25
    =
    1.11
     $=
    1.06
    ="
    1.05
    $=
    1.05
     $=$
    1.02
    $=\
    1.01
    =\
    0.96
    ='
    0.94
     $=\
    0.92
    Activations Density 0.624%

    No Known Activations