© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11071
    Prev
    Next
    INDEX
    Explanations

    the word "upload" and sometimes words related to music or technical writing

    oai_token-act-pair · gemini-2.0-flash

    uploading and adjusting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Majefty
    -1.05
     snippetHide
    -1.01
    NUMX
    -0.98
     pleaſure
    -0.98
     poffible
    -0.98
     HasFactory
    -0.96
     Reſ
    -0.92
     ſta
    -0.91
     ſmall
    -0.91
     fubject
    -0.91
    POSITIVE LOGITS
    <bos>
    0.77
    ↵
    0.69
     P
    0.65
    -
    0.62
     N
    0.61
     The
    0.61
      
    0.59
    ↵↵
    0.58
     T
    0.58
     He
    0.58
    Activations Density 0.622%

    No Known Activations