© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13779
    Prev
    Next
    INDEX
    Explanations

    the word "loss" and words associated with decline

    oai_token-act-pair · gemini-2.0-flash

    loss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    zerland
    -0.62
    +#+#
    -0.57
    ErrUnexpectedEOF
    -0.53
     Explora
    -0.50
    GeoNames
    -0.50
     OnTriggerEnter
    -0.48
    Према
    -0.48
     Domin
    -0.48
    ſelf
    -0.47
    béco
    -0.47
    POSITIVE LOGITS
    imageshack
    0.54
    fromnode
    0.53
     समीक्षाओं
    0.51
     Niedersch
    0.51
    XmlAccessType
    0.50
    ecciones
    0.49
     União
    0.49
     Vann
    0.48
    uxxxx
    0.48
    NUMX
    0.48
    Activations Density 2.011%

    No Known Activations