© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14607
    Prev
    Next
    INDEX
    Explanations

    phrases that could indicate the speaker's attitude or feelings

    oai_token-act-pair · gemini-2.0-flash

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    localctx
    -0.60
    \{\\
    -0.59
     Myron
    -0.59
    álise
    -0.56
    ições
    -0.54
     tori
    -0.53
    ,’’
    -0.52
    ";}
    -0.52
    "}"
    -0.51
     katkıda
    -0.51
    POSITIVE LOGITS
    ftagPool
    0.68
     ویکی‌پدی
    0.64
    IntoConstraints
    0.62
     beginnetje
    0.59
    AddWithValue
    0.59
    UserScript
    0.57
    ربای
    0.54
    انيف
    0.54
    writeFieldEnd
    0.53
    Jereo
    0.52
    Activations Density 7.710%

    No Known Activations