© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4019
    Prev
    Next
    INDEX
    Explanations

    words related to people or entities either as consumers, patients, citizens, subscribers and the like

    oai_token-act-pair · gemini-2.0-flash

    people

    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
     enter
    -0.81
    ColumnHeaders
    -0.68
     experience
    -0.64
    keyframes
    -0.61
    omla
    -0.61
     step
    -0.57
    ModelSerializer
    -0.55
    makeConstraints
    -0.54
     spend
    -0.54
    VersionUID
    -0.54
    POSITIVE LOGITS
    OGND
    0.63
     tartalomajánló
    0.62
    transQ
    0.60
     Lives
    0.59
    __':
    0.57
    suff
    0.57
    RTDA
    0.54
     lives
    0.54
    ніципа
    0.53
     ProtoMessage
    0.52
    Activations Density 4.437%

    No Known Activations