© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12289
    Prev
    Next
    INDEX
    Explanations

    phrases related to marketing and online shopping

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RegressionTest
    -0.44
     tham
    -0.41
    lexia
    -0.40
    complexity
    -0.40
     beantworten
    -0.40
    ysk
    -0.39
    appBar
    -0.38
     grec
    -0.38
     blight
    -0.37
     AttributeSet
    -0.37
    POSITIVE LOGITS
     refroidissement
    0.87
     ſeveral
    0.81
     HttpNotFound
    0.79
     ModelExpression
    0.77
     nevertheless
    0.77
     regarding
    0.77
     charité
    0.76
     Efq
    0.73
     exactly
    0.72
    theless
    0.72
    Activations Density 5.652%

    No Known Activations