© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11591
    Prev
    Next
    INDEX
    Explanations

    words used in conjunction with each other such as for, that, you, to, and and.

    oai_token-act-pair · gemini-2.0-flash

    music

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    CodedInputStream
    -0.41
    remoto
    -0.41
    tał
    -0.41
    coltà
    -0.41
    TagMode
    -0.41
    pula
    -0.41
    épaisseur
    -0.41
     NSError
    -0.41
    PathParam
    -0.41
    hala
    -0.40
    POSITIVE LOGITS
     music
    1.78
     songs
    1.66
     musically
    1.65
     musicians
    1.63
     song
    1.62
     musical
    1.59
     música
    1.55
    music
    1.55
     Music
    1.52
     MUSIC
    1.52
    Activations Density 10.623%

    No Known Activations