© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9011
    Prev
    Next
    INDEX
    Explanations

    words related to music and family

    oai_token-act-pair · gemini-2.0-flash

    Music recording industry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     InputDecoration
    -0.58
    Hentet
    -0.57
     propOrder
    -0.54
    onomía
    -0.52
    SupportActionBar
    -0.48
    VideoCapture
    -0.45
    resultCode
    -0.45
    otro
    -0.44
    RegressionTest
    -0.44
    Revenir
    -0.44
    POSITIVE LOGITS
     record
    1.13
    record
    0.96
     RECORD
    0.84
     Record
    0.81
     album
    0.75
     artist
    0.74
    Record
    0.73
     artists
    0.69
     Artist
    0.67
    RECORD
    0.66
    Activations Density 3.719%

    No Known Activations