© 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. 15784
    Prev
    Next
    INDEX
    Explanations

    words relating to business, politics, personal feelings, time and general adjectives

    oai_token-act-pair · gemini-2.0-flash

    generalities

    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
     Италијани
    -0.97
    <bos>
    -0.90
     Савезне
    -0.87
     indisponible
    -0.85
    хьтан
    -0.84
     Wiktionnaire
    -0.78
    )";
    -0.76
    )");
    -0.75
     disambiguazione
    -0.74
    MLLoader
    -0.73
    POSITIVE LOGITS
     direzione
    0.59
    gulier
    0.57
     fenomeno
    0.57
     méri
    0.57
     exécu
    0.57
     jouets
    0.56
     avulla
    0.56
     besoins
    0.56
     inégal
    0.56
     épais
    0.55
    Activations Density 18.291%

    No Known Activations