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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11198
    Prev
    Next
    INDEX
    Explanations

    words having to do with written language, especially letters and letter frequency

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "sound"

    np_token-act-pair-logits · gpt-4o-mini

    sound

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     OFDb
    -0.70
    RenderAtEndOf
    -0.70
    AnchorStyles
    -0.67
     تانيه
    -0.67
    StructEnd
    -0.67
    tagHelperRunner
    -0.63
    expandindo
    -0.63
    DockStyle
    -0.62
    WindowConstants
    -0.61
    сылкі
    -0.59
    POSITIVE LOGITS
     sounded
    0.65
     sounding
    0.61
     sound
    0.57
    Sound
    0.57
     sounds
    0.53
     sonido
    0.52
    sound
    0.52
     Sound
    0.50
     suono
    0.50
     tabung
    0.49
    Activations Density 1.752%

    No Known Activations