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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15781
    Prev
    Next
    INDEX
    Explanations

    technical nouns used in scientific writing

    oai_token-act-pair · gemini-2.0-flash

    modes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     methodologies
    -1.34
     formats
    -1.29
     strategies
    -1.29
     approaches
    -1.23
     methods
    -1.21
     techniques
    -1.21
     practices
    -1.17
     procedures
    -1.13
     processes
    -1.13
     ways
    -1.11
    POSITIVE LOGITS
     form
    0.68
     mode
    0.68
    styleType
    0.65
     method
    0.63
     bien
    0.54
     model
    0.54
     branch
    0.54
    Бележки
    0.53
     name
    0.53
     way
    0.53
    Activations Density 6.062%

    No Known Activations