© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11698
    Prev
    Next
    INDEX
    Explanations

    terms related to hearing and the ear

    oai_token-act-pair · gemini-2.0-flash

    terms related to hearing and auditory perception

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

    hearing, listening

    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
    Rüyada
    -0.51
     whitespace
    -0.45
    δά
    -0.44
     OTP
    -0.43
    AutoScaleMode
    -0.43
     AFS
    -0.43
     delegado
    -0.43
     calligraphy
    -0.42
    letoe
    -0.41
     ſy
    -0.41
    POSITIVE LOGITS
     listening
    0.79
    abestanden
    0.77
     linkovi
    0.76
     sound
    0.73
     hearing
    0.73
    :✨
    0.72
     heard
    0.71
     hears
    0.71
     listen
    0.70
     propOrder
    0.70
    Activations Density 1.739%

    No Known Activations