© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2100
    Prev
    Next
    INDEX
    Explanations

    tokens that appear in the sentence "break through to the border of the king of fairy"

    oai_token-act-pair · gemini-2.0-flash

    non-English code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Normdatei
    -0.71
    ArrowToggle
    -0.70
     resourceCulture
    -0.69
    Бахар
    -0.65
     AspNetCore
    -0.65
    ManagedBean
    -0.63
     препратки
    -0.63
     >=",
    -0.62
     jScrollPane
    -0.61
    IVEREF
    -0.60
    POSITIVE LOGITS
     فريبيس
    0.55
    voort
    0.47
     indisponible
    0.45
     légiti
    0.42
    fromnode
    0.41
    thoff
    0.41
     dasar
    0.41
     rød
    0.41
     OMITBAD
    0.40
     抽
    0.40
    Activations Density 2.489%

    No Known Activations