© 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. 3890
    Prev
    Next
    INDEX
    Explanations

    instances of researchers drawing conclusions from data

    oai_token-act-pair · gemini-2.0-flash

    statistical estimation

    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
     estimation
    -1.23
     guessing
    -1.16
     Estimation
    -1.16
     guessed
    -1.16
     Estimated
    -1.11
    Estimation
    -1.10
     estimations
    -1.08
    guess
    -1.05
     Estimating
    -1.05
     estimated
    -1.04
    POSITIVE LOGITS
    UserScript
    0.61
    latlng
    0.53
     best
    0.49
    flashdata
    0.48
    ianas
    0.47
    WebControls
    0.44
     שוליים
    0.44
    openqa
    0.43
    opcao
    0.43
    tilia
    0.43
    Activations Density 4.102%

    No Known Activations