© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12501
    Prev
    Next
    INDEX
    Explanations

    words related to bands, music, or records, often alongside function words like "at", "by", "in", "as", "of", "with", "to", and "for."

    oai_token-act-pair · gemini-2.0-flash

    music

    np_max-act-logits · gemini-2.0-flash

    music

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     music
    -2.44
    music
    -2.14
     Music
    -2.13
    Music
    -2.03
     MUSIC
    -1.96
     música
    -1.76
     musique
    -1.75
     Musik
    -1.73
     musik
    -1.68
    MUSIC
    -1.68
    POSITIVE LOGITS
    TagMode
    0.67
    __":
    0.63
     <<<<<<<<<<<<<<
    0.62
     listened
    0.56
    InitVars
    0.56
     listens
    0.54
     pageContext
    0.54
     AssemblyCulture
    0.53
    tagHelperRunner
    0.53
     Cliquez
    0.52
    Activations Density 1.284%

    No Known Activations