© 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. 4416
    Prev
    Next
    INDEX
    Explanations

    words relating to music videos, television shows or artists

    oai_token-act-pair · gemini-2.0-flash

    music videos

    np_max-act-logits · gemini-2.0-flash
    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
     salt
    -0.60
    ✨:
    -0.56
    #
    -0.54
    salt
    -0.54
    zzleHttp
    -0.53
    transmitter
    -0.52
    inette
    -0.52
    ніципа
    -0.52
    NOSIS
    -0.50
     Salt
    -0.48
    POSITIVE LOGITS
     video
    1.38
     videos
    1.29
     Video
    1.24
    video
    1.24
    Video
    1.23
     VIDEO
    1.15
    Videos
    1.08
     Videos
    1.06
     vidéo
    1.05
     videoc
    1.05
    Activations Density 0.491%

    No Known Activations