© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4099
    Prev
    Next
    INDEX
    Explanations

    musical instruments and musical performance

    oai_token-act-pair · gemini-2.0-flash

    musical instruments

    np_max-act-logits · gemini-2.0-flash

    say "instruments" Method used: 2 — tokens after max are instruments

    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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AndEndTag
    -0.83
    BagLayout
    -0.65
    ResumeLayout
    -0.65
    sua
    -0.59
     autorytatywna
    -0.58
    ]<<
    -0.58
    pausal
    -0.57
    <_>
    -0.57
    Espèce
    -0.56
    ativement
    -0.56
    POSITIVE LOGITS
     guitar
    1.19
     piano
    1.06
     bass
    0.96
     violin
    0.93
     guitars
    0.91
     Guitar
    0.88
     Piano
    0.88
    piano
    0.85
     instruments
    0.84
     guitare
    0.84
    Activations Density 0.744%

    No Known Activations