© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10151
    Prev
    Next
    INDEX
    Explanations

    the substring "ze"

    oai_token-act-pair · gemini-2.0-flash

    ze

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    GEBURTSDATUM
    -0.74
     שוליים
    -0.71
    EDEFAULT
    -0.67
    DIPSETTING
    -0.66
    HasColumnType
    -0.65
     CGPoint
    -0.64
    BASEPATH
    -0.63
     상세
    -0.63
     bezeichneter
    -0.62
     consultato
    -0.62
    POSITIVE LOGITS
    middels
    0.46
    mTitle
    0.42
    PyExc
    0.42
    urilor
    0.40
    autoIncrement
    0.39
    说是
    0.39
     mă
    0.39
    ConstraintMaker
    0.39
    MigrationBuilder
    0.38
    Hare
    0.38
    Activations Density 0.273%

    No Known Activations