© 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. 2679
    Prev
    Next
    INDEX
    Explanations

    words commonly used when talking about sound or audio equipment

    oai_token-act-pair · gemini-2.0-flash

    programming code elements or functions

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

    Audio and hearing

    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
     ears
    -1.94
     listening
    -1.91
     listen
    -1.88
     hearing
    -1.87
     listeners
    -1.78
     Listen
    -1.76
     listener
    -1.76
     Listening
    -1.74
     ear
    -1.73
     heard
    -1.73
    POSITIVE LOGITS
    toor
    0.51
     getItemId
    0.42
    ]));
    0.41
     createSprite
    0.40
    ρόν
    0.40
     Pern
    0.40
     Jof
    0.40
     geze
    0.40
    ління
    0.39
     viewing
    0.39
    Activations Density 0.329%

    No Known Activations