© 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. 260
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and legal citations

    oai_token-act-pair · gemini-2.0-flash

    Code and logs

    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
     fusca
    -0.57
     habet
    -0.53
     purpoſe
    -0.53
     ſhould
    -0.51
     ſtate
    -0.50
     uſe
    -0.50
     speciali
    -0.49
     ſtre
    -0.48
     caufe
    -0.48
     tantum
    -0.48
    POSITIVE LOGITS
     arşivlendi
    0.79
     snippetHide
    0.75
    MigrationBuilder
    0.74
    AndEndTag
    0.73
     resourceCulture
    0.73
    expandindo
    0.73
    UserScript
    0.73
    ChildScrollView
    0.73
    Tembelea
    0.72
    ]")]
    0.71
    Activations Density 15.873%

    No Known Activations