© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7507
    Prev
    Next
    INDEX
    Explanations

    mentions of musical instruments, particularly pianos and cellos, and musical recitals

    oai_token-act-pair · gemini-2.0-flash

    musical performances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     condamné
    -0.46
     affaires
    -0.45
    czek
    -0.45
    edom
    -0.44
    +#+
    -0.44
     poil
    -0.44
    RenderAtEndOf
    -0.43
    AppendLine
    -0.43
    tagHelperRunner
    -0.43
     película
    -0.42
    POSITIVE LOGITS
     musical
    0.81
     Италијани
    0.81
     music
    0.75
    musical
    0.75
     singing
    0.68
     musicales
    0.67
     musically
    0.67
     Musical
    0.67
     Music
    0.67
     concert
    0.67
    Activations Density 0.479%

    No Known Activations