© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 3950
    Prev
    Next
    INDEX
    Explanations

    words and acronyms used in scientific or technical contexts

    oai_token-act-pair · gemini-2.0-flash

    code/technical documents

    np_max-act · gemini-2.0-flash

    sentence start Method used: 3 — detected sentence/clause starts; explanation: sentence start

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    numerusform
    -0.93
    UserScript
    -0.92
     CreateTagHelper
    -0.90
    ]--;
    -0.88
     NSCoder
    -0.86
     onOptions
    -0.86
    
    -0.85
    PerformLayout
    -0.84
    .}~\
    -0.84
    !")
    
    -0.84
    POSITIVE LOGITS
    <bos>
    2.48
    '
    0.93
    ↵↵
    0.86
    2
    0.65
    1
    0.65
    ’
    0.65
    M
    0.60
    H
    0.60
     the
    0.59
    I
    0.59
    Activations Density 3.050%

    No Known Activations