© 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. 14437
    Prev
    Next
    INDEX
    Explanations

    HTML tags, especially closing list item tags

    oai_token-act-pair · gemini-2.0-flash

    >

    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
    StoryboardSegue
    -0.72
    PerformLayout
    -0.69
    rawDesc
    -0.66
    قایناق‌لار
    -0.62
    PhysRevD
    -0.60
     beginnetje
    -0.57
    MathML
    -0.56
    gonic
    -0.56
    Tikang
    -0.56
    Personendaten
    -0.55
    POSITIVE LOGITS
     autorytatywna
    0.59
    AnchorStyles
    0.57
     QtGui
    0.46
    tructor
    0.44
     Ihm
    0.43
    iter
    0.43
    ेक
    0.42
    がき
    0.41
     citer
    0.41
    󠁢
    0.41
    Activations Density 1.384%

    No Known Activations