© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6325
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating something is happening to a greater extent.

    oai_token-act-pair · gemini-2.0-flash

    Complete/total adverbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    OrNil
    -0.57
    GOTREF
    -0.57
    Архівовано
    -0.51
    ukone
    -0.51
    PerformLayout
    -0.51
    GEBURTS
    -0.51
     MainAxisSize
    -0.50
    RTEE
    -0.50
     suivantes
    -0.49
     unknownFields
    -0.48
    POSITIVE LOGITS
     completely
    1.13
    completely
    0.95
     Completely
    0.95
     totally
    0.94
    Completely
    0.90
     fully
    0.85
     completamente
    0.82
     entirely
    0.81
     partially
    0.81
     wholly
    0.79
    Activations Density 1.291%

    No Known Activations