© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9697
    Prev
    Next
    INDEX
    Explanations

    LaTeX math symbols and notation

    oai_token-act-pair · gemini-2.0-flash

    terms related to designation or labels

    np_token-act-pair-logits · gpt-4o-mini

    design/signal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     doInBackground
    -0.64
    CodedInputStream
    -0.53
     sheds
    -0.53
     iprot
    -0.51
    Демографія
    -0.51
     Carls
    -0.49
     EDWIN
    -0.49
    }());
    -0.48
    Джерела
    -0.48
    arrête
    -0.48
    POSITIVE LOGITS
     designating
    0.68
    design
    0.66
    Hentet
    0.65
    designation
    0.63
    esign
    0.63
     designation
    0.62
     signal
    0.60
     sign
    0.60
     designate
    0.60
     INDIC
    0.59
    Activations Density 3.587%

    No Known Activations