© 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. 14572
    Prev
    Next
    INDEX
    Explanations

    mentions of tools and equipment

    oai_token-act-pair · gemini-2.0-flash

    tools

    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
    
    -0.96
    ArgsConstructor
    -0.67
    +#+#
    -0.64
    SequentialGroup
    -0.61
     getGroup
    -0.57
    findpost
    -0.57
    bufio
    -0.55
     MaterialApp
    -0.55
     bienvenue
    -0.54
     religieuses
    -0.54
    POSITIVE LOGITS
     bit
    0.68
     BITS
    0.55
    migrationBuilder
    0.55
    Bits
    0.54
     driver
    0.53
     كومونز
    0.53
     springfox
    0.51
     bits
    0.51
     Bit
    0.50
    driver
    0.49
    Activations Density 0.983%

    No Known Activations