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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4684
    Prev
    Next
    INDEX
    Explanations

    a suite of words related to the author's attitude, with a focus on finding words that indicate the writing's persuasive intent.

    oai_token-act-pair · gemini-2.0-flash

    obviousness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     attached
    -0.47
     cross
    -0.44
    ว่า
    -0.43
     AttributeSet
    -0.43
     THAT
    -0.43
     prevent
    -0.43
     mini
    -0.43
    ほど
    -0.43
     tud
    -0.42
    ennett
    -0.42
    POSITIVE LOGITS
     مشين
    0.87
    ReusableCell
    0.74
     Bioaccumulative
    0.72
     betweenstory
    0.69
    IContainer
    0.68
    Bioaccumulative
    0.67
    Brainz
    0.67
    kwür
    0.66
     للاسماء
    0.65
     Seeder
    0.64
    Activations Density 3.543%

    No Known Activations