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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10415
    Prev
    Next
    INDEX
    Explanations

    words related to media playing and technical configurations

    oai_token-act-pair · gemini-2.0-flash

    Sound and audio

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     विश्वसनीयता
    -0.63
    脚注の使い方
    -0.63
    évaluateur
    -0.58
    AccessorTable
    -0.57
     Infórmanos
    -0.56
     }{@
    -0.55
    ArgsConstructor
    -0.54
    AccessFile
    -0.52
    illium
    -0.50
    spora
    -0.50
    POSITIVE LOGITS
     sound
    1.00
    sound
    0.87
    Sound
    0.84
     Sound
    0.80
     audio
    0.75
     SOUND
    0.72
    audio
    0.69
     subtitle
    0.68
     Audio
    0.68
    SOUND
    0.67
    Activations Density 0.963%

    No Known Activations