© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3750
    Prev
    Next
    INDEX
    Explanations

    words related to the author's perspective, feelings, or opinions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ]--;
    -0.61
    bootstrapcdn
    -0.60
    TagMode
    -0.59
    cyjna
    -0.56
    Poloha
    -0.52
    LikeLiked
    -0.50
    disclosure
    -0.49
    jsdelivr
    -0.49
     Lumpur
    -0.49
    gettyimages
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.62
     fucked
    0.62
    ArgsConstructor
    0.56
     shitty
    0.55
     insane
    0.54
     nahilalakip
    0.53
     gonna
    0.53
    شهاد
    0.50
    پیوند
    0.49
     crazy
    0.49
    Activations Density 2.284%

    No Known Activations