© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3194
    Prev
    Next
    INDEX
    Explanations

    descriptive language about music or the music industry

    oai_token-act-pair · gemini-2.0-flash

    Music reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ConstraintMaker
    -0.63
    wood
    -0.43
     spake
    -0.42
    SPOILERS
    -0.42
    [:-
    -0.41
    InputBorder
    -0.40
    googleapis
    -0.40
     kür
    -0.40
     trás
    -0.39
     bort
    -0.39
    POSITIVE LOGITS
    حياتها
    0.74
     ModelExpression
    0.69
     lenker
    0.67
     melodic
    0.64
     songwriting
    0.63
     getItemCount
    0.63
     sonic
    0.61
     recul
    0.61
     instrumental
    0.60
     melodies
    0.60
    Activations Density 2.022%

    No Known Activations