© 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. 11599
    Prev
    Next
    INDEX
    Explanations

    code excerpts with keywords 'module', 'Mappings', 'props', 'boxes or 'names' connected by a dot

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    lagt
    -0.45
    isMethod
    -0.41
    GetInstance
    -0.40
    velocityY
    -0.40
     material
    -0.39
     espèce
    -0.39
    ceau
    -0.38
    enderror
    -0.38
     note
    -0.38
    ěstí
    -0.38
    POSITIVE LOGITS
    xase
    0.79
    Bioaccumulative
    0.79
    ftagPool
    0.78
     Roskov
    0.77
     يتيمه
    0.75
    ="@+
    0.74
    TagMode
    0.72
    tagHelperRunner
    0.67
     ComVisible
    0.67
    ConstraintMaker
    0.65
    Activations Density 0.303%

    No Known Activations