© 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. 12754
    Prev
    Next
    INDEX
    Explanations

    lines of code starting with a comment character like '*' or '/'

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    complexContent
    -1.10
    StoryboardSegue
    -1.00
    tagHelperRunner
    -1.00
     Administrativna
    -0.97
    Tikang
    -0.95
     незавершена
    -0.95
     TextInputType
    -0.94
    ^(@)
    -0.92
    Personendaten
    -0.88
    ̈́
    -0.87
    POSITIVE LOGITS
    Save
    0.43
    ชั่น
    0.41
    vari
    0.40
    늘
    0.39
    fin
    0.39
     لق
    0.38
     var
    0.38
     
    0.38
     First
    0.37
    First
    0.37
    Activations Density 1.230%

    No Known Activations