© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12273
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing possibility or obligation

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ///</
    -0.62
    StructEnd
    -0.60
    ranges
    -0.59
     ranges
    -0.59
     تضيفلها
    -0.58
     Pind
    -0.57
    rovnik
    -0.57
    UnusedPrivate
    -0.57
    tagext
    -0.55
     Sorte
    -0.53
    POSITIVE LOGITS
    PRWEB
    0.52
    ualla
    0.49
    stadt
    0.46
    zido
    0.46
    wicklung
    0.46
    enna
    0.46
    bilan
    0.45
     prosent
    0.45
     keten
    0.44
    argli
    0.43
    Activations Density 1.906%

    No Known Activations