© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3984
    Prev
    Next
    INDEX
    Explanations

    proper nouns or acronyms, particularly those related to technology and business

    oai_token-act-pair · gemini-2.0-flash

    File directories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ostavi
    -0.63
    <bos>
    -0.51
    migrationBuilder
    -0.50
    rels
    -0.46
    Reception
    -0.45
    رك
    -0.45
     deleteById
    -0.45
    jspx
    -0.44
     giác
    -0.44
    TemporalType
    -0.43
    POSITIVE LOGITS
    agisse
    0.62
     ivelany
    0.61
     FetchType
    0.61
    EDEFAULT
    0.60
    VIAF
    0.60
     quæ
    0.59
     SwitchCompat
    0.59
    GOTREF
    0.59
    OptionsMenu
    0.58
    довлет
    0.57
    Activations Density 1.149%

    No Known Activations