© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2539
    Prev
    Next
    INDEX
    Explanations

    passive voice verbs, and related adjectives, describing processes

    oai_token-act-pair · gemini-2.0-flash

    technical processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     S
    -0.46
    cemment
    -0.46
    lorus
    -0.45
    Slut
    -0.44
    相关文章
    -0.44
    kező
    -0.43
    openhauer
    -0.43
    Carriera
    -0.43
     Scan
    -0.42
    gdx
    -0.42
    POSITIVE LOGITS
     handled
    0.81
    rungsseite
    0.79
    клопе
    0.75
     verzorg
    0.69
     StringTokenizer
    0.69
    handled
    0.65
    migrationBuilder
    0.63
     Roskov
    0.62
     ***!
    0.60
    StoryboardSegue
    0.60
    Activations Density 2.834%

    No Known Activations