© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9077
    Prev
    Next
    INDEX
    Explanations

    strings of lowercase letters separated by underscores and superscripted numbers, potentially representing mathematical or scientific notation, or more simply, it finds subscripts

    oai_token-act-pair · gemini-2.0-flash

    j

    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
    2
    -1.73
     twenty
    -1.36
     Twenty
    -1.23
    ２
    -1.16
     TWENTY
    -1.13
    twenty
    -1.00
    Twenty
    -0.99
    ২
    -0.98
     ٢
    -0.96
     vingt
    -0.93
    POSITIVE LOGITS
    IVEREF
    0.57
    StoryboardSegue
    0.51
    featureID
    0.51
    rlpool
    0.51
     lenker
    0.47
     لينك
    0.44
    ="@+
    0.44
    HomeAsUpEnabled
    0.43
    cadilly
    0.43
    WebVitals
    0.41
    Activations Density 0.962%

    No Known Activations