© 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. 13962
    Prev
    Next
    INDEX
    Explanations

    instances where research "indicates" or "suggests" a conclusion or relationship

    oai_token-act-pair · gemini-2.0-flash

    indicating/suggesting

    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
    算
    -0.49
    قایناقلار
    -0.45
    离
    -0.43
    AnimationsModule
    -0.43
     commerciaux
    -0.42
     Australie
    -0.41
    面
    -0.40
     prezen
    -0.40
     pieno
    -0.39
     muestra
    -0.39
    POSITIVE LOGITS
     AssemblyTitle
    0.84
     وتسجيلات
    0.71
      (
    0.71
    ]').
    0.71
    ✨:
    0.70
     ujednoznacz
    0.70
     ModelExpression
    0.69
    لينكات
    0.68
     onCreateView
    0.68
    ingin
    0.66
    Activations Density 0.457%

    No Known Activations