© 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. 9927
    Prev
    Next
    INDEX
    Explanations

    personal commentary in the text, written in first person.

    oai_token-act-pair · gemini-2.0-flash

    quantity/intensity

    np_max-act-logits · gemini-2.0-flash

    quantity words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    TagMode
    -0.75
    +#+#
    -0.73
    expandindo
    -0.71
     BoxFit
    -0.71
     Tym
    -0.69
    RTEE
    -0.69
     AssemblyCulture
    -0.69
    ContentAlignment
    -0.68
     Thine
    -0.68
     resourceCulture
    -0.67
    POSITIVE LOGITS
     lots
    0.59
     so
    0.59
     Lots
    0.56
     lot
    0.53
    Lots
    0.49
     which
    0.49
     whether
    0.46
    lots
    0.46
     LOTS
    0.46
     plenty
    0.43
    Activations Density 13.844%

    No Known Activations