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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3268
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to audio recording and broadcast hardware

    oai_token-act-pair · gemini-2.0-flash

    microphone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    setVerticalGroup
    -0.55
    +#+
    -0.54
    Obrázky
    -0.53
    vega
    -0.50
     tark
    -0.47
    Filmografie
    -0.47
    UEZ
    -0.46
    lanta
    -0.45
    <bos>
    -0.45
     visual
    -0.45
    POSITIVE LOGITS
     vocals
    0.75
     listeners
    0.71
     trumpets
    0.70
     listener
    0.69
    Audio
    0.68
     audio
    0.68
     podcasts
    0.68
     sounding
    0.68
     Audible
    0.65
     SoundCloud
    0.65
    Activations Density 8.589%

    No Known Activations