© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10933
    Prev
    Next
    INDEX
    Explanations

    mentions of studio equipment and upgrades in the context of audio recording and playback.

    oai_token-act-pair · gemini-2.0-flash

    improvements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ECL
    -0.50
     Audiodateien
    -0.49
    ggior
    -0.49
     mara
    -0.48
    tableFuture
    -0.46
     couple
    -0.46
     zonal
    -0.45
     integra
    -0.45
     ligiloj
    -0.44
     Zwer
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.72
     صوتيه
    0.66
     onCreateView
    0.63
    MigrationBuilder
    0.61
     وتسجيلات
    0.59
    Демографія
    0.57
     Taktlose
    0.55
    yntaxException
    0.55
    UnsafeEnabled
    0.54
     externi
    0.53
    Activations Density 1.179%

    No Known Activations