© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12145
    Prev
    Next
    INDEX
    Explanations

    statistics and words that denote winning or losing

    oai_token-act-pair · gemini-2.0-flash

    numerical values and terms related to scoring

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    TagMode
    -0.96
     виправивши
    -0.90
    httphttps
    -0.85
     &___
    -0.82
     ModelExpression
    -0.81
    الحياه
    -0.79
    MLLoader
    -0.79
     myſelf
    -0.79
    DrawerToggle
    -0.77
     tartalomajánló
    -0.77
    POSITIVE LOGITS
     judge
    0.49
     test
    0.47
    adio
    0.45
     droit
    0.43
    nos
    0.43
    M
    0.43
    ud
    0.41
    ient
    0.41
     point
    0.41
     use
    0.40
    Activations Density 0.380%

    No Known Activations