© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16152
    Prev
    Next
    INDEX
    Explanations

    words that are related to audio, sound, and music

    oai_token-act-pair · gemini-2.0-flash

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     pidana
    -0.47
     inoxydable
    -0.44
    clerview
    -0.44
     hombros
    -0.42
    toLowerCase
    -0.42
    jTable
    -0.42
    CharStream
    -0.41
     ACCEPT
    -0.41
    dihydro
    -0.40
     residencial
    -0.40
    POSITIVE LOGITS
    rungsseite
    0.86
     متعلقه
    0.84
     nahilalakip
    0.79
    Tembelea
    0.79
    MessageTagHelper
    0.76
    Pautan
    0.73
    +#+#
    0.69
     autorytatywna
    0.67
    aarrggbb
    0.66
    ApiModelProperty
    0.66
    Activations Density 3.312%

    No Known Activations