© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11517
    Prev
    Next
    INDEX
    Explanations

    phrases that convey warnings or negative sentiment

    oai_token-act-pair · gemini-2.0-flash

    terms related to warnings or caution

    np_token-act-pair-logits · gpt-4o-mini

    negative contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     mày
    -0.52
    getMenuInflater
    -0.52
     يتيمه
    -0.51
    ousands
    -0.51
     الدولى
    -0.49
    \{\\
    -0.49
     Yugoslav
    -0.49
    كويكب
    -0.48
     ͡°
    -0.48
     pæ
    -0.48
    POSITIVE LOGITS
     overshadowed
    0.62
     GenerationType
    0.59
    classnames
    0.58
     lost
    0.58
     spoilt
    0.57
     AssemblyCulture
    0.56
     Defeat
    0.56
    IntoConstraints
    0.54
     viewType
    0.54
     defeat
    0.54
    Activations Density 2.745%

    No Known Activations