© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10044
    Prev
    Next
    INDEX
    Explanations

    project names, work roles, and types of documents

    oai_token-act-pair · gemini-2.0-flash

    project

    np_max-act · gemini-2.0-flash
    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
     يتيمه
    -1.10
    findpost
    -1.05
     nakalista
    -0.94
    ftagPool
    -0.93
    KommentareTeilen
    -0.91
    contentLoaded
    -0.91
     محفوظة
    -0.89
    GraphicsUnit
    -0.85
    '));
    -0.84
    MLLoader
    -0.83
    POSITIVE LOGITS
     respectfully
    0.58
     fairly
    0.53
    slightly
    0.50
     appropriately
    0.50
     pungkasnya
    0.50
    somewhat
    0.49
     modestly
    0.49
     correctly
    0.49
     bastante
    0.49
     suitably
    0.48
    Activations Density 5.424%

    No Known Activations