© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 580
    Prev
    Next
    INDEX
    Explanations

    Danish words in movie reviews.

    oai_token-act-pair · gemini-2.0-flash

    Three, Four

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    six
    -0.46
    ाहरण
    -0.44
     ten
    -0.44
     getModel
    -0.42
    Referências
    -0.42
     iLocal
    -0.42
     balanceOf
    -0.42
     eleven
    -0.42
     viewDidLoad
    -0.42
    ApiModelProperty
    -0.42
    POSITIVE LOGITS
     tre
    1.11
     due
    1.07
    due
    0.90
     Due
    0.89
     fire
    0.86
    Due
    0.85
     DUE
    0.84
    Tre
    0.74
     Tre
    0.72
     Fire
    0.72
    Activations Density 0.348%

    No Known Activations