© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15826
    Prev
    Next
    INDEX
    Explanations

    research papers that discuss what has been studied to date

    oai_token-act-pair · gemini-2.0-flash

    say "date"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SharedCtor
    -0.87
    StructEnd
    -0.85
    libft
    -0.79
     resourceCulture
    -0.77
    AndEndTag
    -0.76
    tagHelperRunner
    -0.76
    yntaxException
    -0.73
    PhysRev
    -0.72
    BindingResult
    -0.71
     مرئيه
    -0.68
    POSITIVE LOGITS
     to
    2.03
     date
    1.74
    date
    1.51
     To
    1.26
    to
    1.24
     Date
    1.22
    Date
    1.20
     DATE
    1.19
    To
    1.16
     TO
    1.10
    Activations Density 2.010%

    No Known Activations