© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9671
    Prev
    Next
    INDEX
    Explanations

    javadoc-style references to code elements

    oai_token-act-pair · gemini-2.0-flash

    link

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ,
    -0.59
    .
    -0.57
     and
    -0.56
     direct
    -0.49
     plus
    -0.48
     but
    -0.47
    str
    -0.46
     so
    -0.46
     model
    -0.45
     page
    -0.45
    POSITIVE LOGITS
    ArgsConstructor
    1.41
    complexContent
    1.37
    Personendaten
    1.32
    yntaxException
    1.23
    __":
    1.18
    MockBean
    1.15
    __':
    1.14
    #+#
    1.13
     betweenstory
    1.13
     kaarangay
    1.13
    Activations Density 0.809%

    No Known Activations