Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9511
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially those including the symbols '±' and '.'

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     themſelves
    -0.86
     himſelf
    -0.85
     raiſ
    -0.84
     myſelf
    -0.84
     ſeveral
    -0.80
     purpoſe
    -0.80
     pleaſure
    -0.77
     uſe
    -0.77
     fhew
    -0.77
     ſmall
    -0.75
    POSITIVE LOGITS
    脚注の使い方
    0.73
    RenderAtEndOf
    0.73
    +#+#
    0.73
    !*\
    0.72
    PreferredItem
    0.72
     nakalista
    0.71
    تقاوى
    0.70
    #+#
    0.69
    rungsseite
    0.69
     <=",
    0.68
    Activations Density 28.131%

    No Known Activations