Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9609
    Prev
    Next
    INDEX
    Explanations

    words associated with negative emotions, conflict, and their causes

    oai_token-act-pair · gemini-2.0-flash

    Causing problems/distess

    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
    mybatisplus
    -0.64
    ">//
    -0.52
    thâu
    -0.50
    WithIOException
    -0.49
    +#+#
    -0.48
    major
    -0.48
     major
    -0.47
    bors
    -0.46
    ftagPool
    -0.46
     maior
    -0.46
    POSITIVE LOGITS
     Chriftian
    0.63
    tvguidetime
    0.63
    WebElementEntity
    0.62
    toHaveBeenCalled
    0.60
    Interpolator
    0.58
     ſtate
    0.56
    Captor
    0.55
     ftate
    0.55
     Jefus
    0.55
     demurrer
    0.54
    Activations Density 14.283%

    No Known Activations