© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14577
    Prev
    Next
    INDEX
    Explanations

    code, medical imaging, and scientific writing

    oai_token-act-pair · gemini-2.0-flash

    programming variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     CreateTagHelper
    -1.15
     betweenstory
    -1.04
    MessageOf
    -0.86
     Majefty
    -0.82
     faſt
    -0.81
     Jefus
    -0.81
     Efq
    -0.81
     myſelf
    -0.79
     poffe
    -0.79
     pleaſure
    -0.78
    POSITIVE LOGITS
    til
    0.48
     san
    0.47
    comp
    0.46
     ...
    0.46
     comp
    0.44
     m
    0.44
    Comp
    0.43
     man
    0.42
    </em>
    0.42
    le
    0.42
    Activations Density 8.444%

    No Known Activations