© 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. 9510
    Prev
    Next
    INDEX
    Explanations

    XML code

    oai_token-act-pair · gemini-2.0-flash

    multi-character sequences starting with 'X'

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

    X

    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
     Tate
    -0.52
     @"/
    -0.49
     Taylor
    -0.48
     Ta
    -0.48
    usercontent
    -0.48
    consulté
    -0.46
     vem
    -0.46
    Tate
    -0.45
    retz
    -0.45
     each
    -0.43
    POSITIVE LOGITS
    GOTREF
    0.73
     للاسماء
    0.71
    SBATCH
    0.71
    BeginContext
    0.69
     nakalista
    0.68
     ProtoMessage
    0.68
     intptr
    0.68
    MLLoader
    0.68
    aarrggbb
    0.67
    Geplaatst
    0.65
    Activations Density 0.521%

    No Known Activations