© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14666
    Prev
    Next
    INDEX
    Explanations

    code snippets and HTML form elements

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Interface
    -0.41
    stretchr
    -0.41
    Apple
    -0.39
    cho
    -0.37
    Claims
    -0.37
     O
    -0.36
     claimed
    -0.36
    qui
    -0.36
     claim
    -0.36
     il
    -0.35
    POSITIVE LOGITS
    ьаж
    0.85
     iſt
    0.84
    Personendaten
    0.81
     Eſ
    0.81
     Monfieur
    0.79
     againſt
    0.79
     مواليد
    0.77
     ſind
    0.77
     BoxFit
    0.77
     Theſe
    0.75
    Activations Density 1.918%

    No Known Activations