© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15940
    Prev
    Next
    INDEX
    Explanations

    the start of a scientific study about health, medical conditions, or treatment

    oai_token-act-pair · gemini-2.0-flash

    were

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     subject
    -0.50
     SUBJECT
    -0.47
     subjects
    -0.44
     study
    -0.44
    study
    -0.43
     star
    -0.43
     estrella
    -0.43
    Study
    -0.42
     Drill
    -0.42
     Subject
    -0.41
    POSITIVE LOGITS
    adaptiveStyles
    0.72
    脚注の使い方
    0.71
    gameserver
    0.68
    SBATCH
    0.66
     disambiguazione
    0.66
     disponibilités
    0.65
    StoryboardSegue
    0.65
    InstanceState
    0.64
     विश्वसनीयता
    0.64
    таратура
    0.64
    Activations Density 20.805%

    No Known Activations