© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9585
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to music and online videos

    oai_token-act-pair · gemini-2.0-flash

    songs

    np_max-act · gemini-2.0-flash

    song

    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     wij
    -0.45
    WithType
    -0.39
     dago
    -0.36
     dre
    -0.36
    AutoScaleMode
    -0.35
     mercados
    -0.35
     tenter
    -0.34
    RIST
    -0.34
    τώ
    -0.34
    ferrer
    -0.34
    POSITIVE LOGITS
     songs
    1.39
     song
    1.32
     Songs
    1.18
    Songs
    1.17
    songs
    1.15
     lyrics
    1.11
     SONGS
    1.11
    Song
    1.11
     hymns
    1.10
     music
    1.09
    Activations Density 0.629%

    No Known Activations