© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13167
    Prev
    Next
    INDEX
    Explanations

    text breaks

    oai_token-act-pair · gemini-2.0-flash

    nature trails

    np_max-act · 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
    CppMethod
    -0.88
    PMailer
    -0.75
    featureID
    -0.68
    SOUNDBITE
    -0.65
    Geplaatst
    -0.63
    <bos>
    -0.61
     Mej
    -0.61
    AndEndTag
    -0.61
    tangentMode
    -0.59
     мәкал
    -0.59
    POSITIVE LOGITS
     Sorry
    0.35
    barui
    0.35
     mewakili
    0.35
    RAINT
    0.34
    Sorry
    0.34
     represents
    0.34
    felizmente
    0.32
    earcher
    0.32
    ftant
    0.32
    jointed
    0.32
    Activations Density 0.045%

    No Known Activations