© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6883
    Prev
    Next
    INDEX
    Explanations

    food recipes

    oai_token-act-pair · gemini-2.0-flash

    cooking, recipes and preparation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     JpaRepository
    -0.71
     GenerationType
    -0.69
     AssemblyTitle
    -0.65
    __':
    -0.65
    IsContent
    -0.62
     actionMode
    -0.61
    
    -0.60
    TemporalType
    -0.60
     Pingback
    -0.59
     FAP
    -0.59
    POSITIVE LOGITS
     nahilalakip
    0.74
    libft
    0.53
     score
    0.48
    écial
    0.48
     Super
    0.46
    bindValue
    0.46
    taobao
    0.44
    纂
    0.44
    ecake
    0.44
     super
    0.43
    Activations Density 1.222%

    No Known Activations