© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15175
    Prev
    Next
    INDEX
    Explanations

    words related to default computer audio devices and speech synthesis

    oai_token-act-pair · gemini-2.0-flash

    terms related to audio or sound

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

    audio 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
    VersionUID
    -0.69
     الرياضيه
    -0.52
    NetworkInfo
    -0.49
    HomeAsUpEnabled
    -0.46
     pstmt
    -0.45
     Jof
    -0.45
    taxis
    -0.44
     Voulez
    -0.44
    DoubleQuotes
    -0.44
    omitempty
    -0.43
    POSITIVE LOGITS
     sound
    1.60
     audio
    1.57
     Sound
    1.48
    sound
    1.47
    Sound
    1.44
     Audio
    1.40
     SOUND
    1.38
     sounds
    1.34
    audio
    1.34
     voice
    1.33
    Activations Density 17.104%

    No Known Activations