© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8608
    Prev
    Next
    INDEX
    Explanations

    legal and statistical terminology about responsibility and recovery

    oai_token-act-pair · gemini-2.0-flash

    legal and mathematical topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ள்
    -0.46
     constitue
    -0.41
     baie
    -0.40
     nije
    -0.40
     brindar
    -0.39
     fede
    -0.39
    会議
    -0.39
    odom
    -0.39
     N
    -0.38
     pok
    -0.38
    POSITIVE LOGITS
    Demografia
    0.76
    RenderAtEndOf
    0.73
     Chwiliwch
    0.73
    >*/
    0.70
    DeleteBehavior
    0.69
     muualla
    0.68
    uxxxx
    0.67
    RegistryLite
    0.66
    jooq
    0.66
    ſelf
    0.66
    Activations Density 2.908%

    No Known Activations