© 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. 13281
    Prev
    Next
    INDEX
    Explanations

    code snippets containing editing and creating operations

    oai_token-act-pair · gemini-2.0-flash

    programming

    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
    PYX
    -0.60
     snippetHide
    -0.59
     "..\..\..\
    -0.58
     MainAxisSize
    -0.57
    новништво
    -0.56
    himovic
    -0.55
    DotNetBar
    -0.54
    jstor
    -0.53
    enumii
    -0.52
     Vou
    -0.50
    POSITIVE LOGITS
     AssemblyCompany
    0.71
    GeoNames
    0.50
    Espèce
    0.49
    IBarButtonItem
    0.48
    λιο
    0.47
     dataSnapshot
    0.46
    UpInside
    0.45
     فہرست
    0.44
    Portale
    0.44
     indisponible
    0.44
    Activations Density 3.530%

    No Known Activations