© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10179
    Prev
    Next
    INDEX
    Explanations

    HTML image links and attributes

    oai_token-act-pair · gemini-2.0-flash

    img

    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
    UnsafeEnabled
    -0.69
     Efq
    -0.68
     whoſe
    -0.64
     Chriftian
    -0.63
    adaptiveStyles
    -0.62
    ISupport
    -0.62
    GEBURTSDATUM
    -0.61
     vPvB
    -0.60
    EDEFAULT
    -0.59
     JpaRepository
    -0.59
    POSITIVE LOGITS
     đội
    0.44
    Koordinaten
    0.42
    .:
    0.40
    dymyr
    0.40
    вань
    0.40
    ToBounds
    0.39
     broad
    0.39
    országban
    0.39
     hati
    0.39
    Begriffsklä
    0.39
    Activations Density 2.658%

    No Known Activations