© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11255
    Prev
    Next
    INDEX
    Explanations

    words in Croatian.

    oai_token-act-pair · gemini-2.0-flash

    Facebook Account Kit (foreign language)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ourite
    -0.77
    ientôt
    -0.68
    ceptre
    -0.68
    Ừ
    -0.65
    igenous
    -0.64
    unicip
    -0.64
     sandero
    -0.64
    erapa
    -0.64
    igration
    -0.64
    ousands
    -0.64
    POSITIVE LOGITS
    <bos>
    2.27
    تقاوى
    0.68
    ’
    0.58
     AssemblyTitle
    0.57
    Билгалдахарш
    0.57
    styleType
    0.56
     kasarigan
    0.54
     '\\;'
    0.54
    defineProperty
    0.50
    '
    0.50
    Activations Density 1.208%

    No Known Activations