© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3755
    Prev
    Next
    INDEX
    Explanations

    commas, periods, pronouns and conjunctions, as well as some common words such as "the", "that", "if", and "also"

    oai_token-act-pair · gemini-2.0-flash

    ","

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    (
    -0.41
    -0.41
    ;
    -0.38
    ,
    -0.35
     così
    -0.34
     alfo
    -0.33
     Bucure
    -0.32
     palestra
    -0.32
    )++;
    -0.32
    :+:
    -0.31
    POSITIVE LOGITS
    <bos>
    0.88
     CreateTagHelper
    0.84
    ValueStyle
    0.77
     initComponents
    0.75
    GEBURTSDATUM
    0.73
    contentLoaded
    0.71
    SourceChecksum
    0.70
     we
    0.69
    StoryboardSegue
    0.68
     you
    0.66
    Activations Density 7.591%
    No Known Activations