© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 673
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns near adjectives

    oai_token-act-pair · gemini-2.0-flash

    ownership, association, or relationship

    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
     getchar
    -0.50
    zul
    -0.49
    HasOne
    -0.49
    anger
    -0.48
    fastjson
    -0.48
    enging
    -0.48
     aus
    -0.47
     EXC
    -0.47
    ysz
    -0.47
    WEL
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.59
    Personensuche
    0.59
    tagHelperRunner
    0.59
    WebVitals
    0.57
    شهاد
    0.53
    MigrationBuilder
    0.53
    IContainer
    0.51
    serviceWorker
    0.51
    ötzlich
    0.50
    GEBURTSDATUM
    0.50
    Activations Density 6.404%

    No Known Activations