© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12636
    Prev
    Next
    INDEX
    Explanations

    legal citations

    oai_token-act-pair · gemini-2.0-flash

    en dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     للمعارف
    -0.68
    atimes
    -0.60
     mecán
    -0.56
    `]
    -0.55
    argout
    -0.54
    sbereich
    -0.54
     linkovi
    -0.53
    kloped
    -0.53
     дописавши
    -0.53
    Démographie
    -0.53
    POSITIVE LOGITS
    fjspx
    0.59
    ArgsConstructor
    0.52
     mergeFrom
    0.51
    
    0.48
     extends
    0.48
     disbur
    0.47
     ProtoMessage
    0.46
     iprot
    0.46
    ImageContext
    0.45
    DebuggerNonUser
    0.45
    Activations Density 11.375%

    No Known Activations