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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8580
    Prev
    Next
    INDEX
    Explanations

    words in a text about audio mixing that describe modifying sound frequencies and the degree of bass present

    oai_token-act-pair · gemini-2.0-flash

    Film/technical context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SharedCtor
    -0.62
    WithIOException
    -0.61
    Хьажоргаш
    -0.58
    complexContent
    -0.57
    PDATE
    -0.56
     useCallback
    -0.55
    ]")]
    -0.55
    __(/*!
    -0.54
    TypedDataSet
    -0.54
    énario
    -0.54
    POSITIVE LOGITS
    Autoritní
    0.63
     pública
    0.53
     juridiques
    0.50
     blessés
    0.47
     권
    0.47
     religieuses
    0.46
    tamo
    0.45
     pantaloni
    0.44
     MATHEMATICAL
    0.44
     láser
    0.44
    Activations Density 4.064%

    No Known Activations