© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14862
    Prev
    Next
    INDEX
    Explanations

    words relating to financial offers and services, especially those involving tailoring products to suit individual needs

    oai_token-act-pair · gemini-2.0-flash

    comfortably

    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
    PhysRevD
    -0.65
    ScopeManager
    -0.55
    titleMargin
    -0.49
    ->___
    -0.49
     Lordships
    -0.48
     Roadster
    -0.48
    Hahahahaha
    -0.48
    thâu
    -0.48
     saurait
    -0.46
    AccessorTable
    -0.46
    POSITIVE LOGITS
    slidesPer
    0.60
    jublj
    0.59
    oa̍t
    0.59
    MarshalTo
    0.59
     мѣ
    0.58
    ajoz
    0.57
     crown
    0.56
    KURZBESCHREIBUNG
    0.55
    momix
    0.54
    apha
    0.54
    Activations Density 2.444%

    No Known Activations