© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8760
    Prev
    Next
    INDEX
    Explanations

    music-related superlatives and descriptors

    oai_token-act-pair · gemini-2.0-flash

    a mix of cultural references and musical terms

    np_token-act-pair-logits · gpt-4o-mini

    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_21/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.21.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
    bl
    -0.47
    furt
    -0.45
    bleven
    -0.39
    Fu
    -0.37
    Bl
    -0.37
     continuing
    -0.36
     Hage
    -0.36
    pois
    -0.36
     Satz
    -0.36
     czyn
    -0.35
    POSITIVE LOGITS
    Portail
    0.94
    WriteBarrier
    0.87
    Personendaten
    0.82
     kasarigan
    0.82
    encodeWith
    0.80
    Geplaatst
    0.79
    ########.
    0.78
    Personensuche
    0.78
    djangoproject
    0.74
     nahilalakip
    0.73
    Activations Density 1.204%

    No Known Activations