© 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. 6724
    Prev
    Next
    INDEX
    Explanations

    words associated with music albums, tracks, and releases

    oai_token-act-pair · gemini-2.0-flash

    Music albums

    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
    SuccessListener
    -0.72
    providedIn
    -0.60
     katal
    -0.57
     invokingState
    -0.56
    jectures
    -0.55
     roleId
    -0.54
     Sera
    -0.51
    خصة
    -0.50
    localctx
    -0.50
    abestanden
    -0.50
    POSITIVE LOGITS
     Bré
    0.47
    stdc
    0.47
    ekš
    0.46
     kasarigan
    0.45
     ""));
    0.43
    BagLayout
    0.42
    Trademark
    0.42
    posedge
    0.42
    Fandom
    0.42
    ();)
    0.41
    Activations Density 8.901%

    No Known Activations