© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3992
    Prev
    Next
    INDEX
    Explanations

    html tags and snippets in multiple languages

    oai_token-act-pair · gemini-2.0-flash

    computer 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     was
    -2.02
    was
    -1.50
    Was
    -1.45
     Was
    -1.43
     were
    -1.26
     WAS
    -1.15
     был
    -1.14
     была
    -1.14
     était
    -1.11
     був
    -1.03
    POSITIVE LOGITS
    StoryboardSegue
    0.72
    enumi
    0.69
    RenderAtEndOf
    0.64
    principalColumn
    0.58
    出版年
    0.58
    glBindBuffer
    0.58
    featureID
    0.58
     AttributeSet
    0.57
    IndentedString
    0.57
    ⓧ
    0.56
    Activations Density 1.205%

    No Known Activations