© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13493
    Prev
    Next
    INDEX
    Explanations

    hexadecimal byte strings and sequences of hexadecimal byte strings separated by commas, plus signs, and whitespace

    oai_token-act-pair · gemini-2.0-flash

    hexadecimal/Unicode sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     autorytatywna
    -1.02
     فريبيس
    -0.88
    ंदीखरीदारी
    -0.86
     للاسماء
    -0.84
    ])));
    -0.81
    AccessorTable
    -0.80
     Савезне
    -0.80
     سكانية
    -0.78
     виправивши
    -0.78
     Réponses
    -0.77
    POSITIVE LOGITS
    夠
    0.46
     Broken
    0.46
     foon
    0.45
    ţe
    0.42
    AtPosition
    0.42
     Vorstellung
    0.41
     υπό
    0.41
    ämmer
    0.41
     dne
    0.40
     noix
    0.40
    Activations Density 8.296%

    No Known Activations