© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14562
    Prev
    Next
    INDEX
    Explanations

    text classifying content or describing the classification of a species of flies

    oai_token-act-pair · gemini-2.0-flash

    Art crafting modification

    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
     script
    -0.94
     writing
    -0.93
     characters
    -0.90
    Writing
    -0.84
     Writing
    -0.82
    writing
    -0.80
     Script
    -0.80
     scripts
    -0.78
    script
    -0.73
    Script
    -0.72
    POSITIVE LOGITS
     odkazy
    0.64
    adpleegd
    0.64
     noDo
    0.63
    脚注の使い方
    0.59
    EDEFAULT
    0.57
     виправивши
    0.53
    FormState
    0.52
    სქოლიო
    0.52
     Perla
    0.52
     дописавши
    0.51
    Activations Density 0.625%

    No Known Activations