© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 249
    Prev
    Next
    INDEX
    Explanations

    negative statements, especially those including possessive pronouns or indefinite articles

    oai_token-act-pair · gemini-2.0-flash

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     a
    -0.72
     the
    -0.65
     anything
    -0.56
     any
    -0.48
     their
    -0.48
     your
    -0.48
     and
    -0.48
     our
    -0.48
    sinon
    -0.45
     constantemente
    -0.45
    POSITIVE LOGITS
    RenderAtEndOf
    0.67
    AddTagHelper
    0.63
     AssemblyTitle
    0.63
    StoreMessageInfo
    0.63
    UnusedPrivate
    0.59
     niyang
    0.59
    Semitic
    0.57
    AndEndTag
    0.57
    HtmlAttribute
    0.55
    SceneManagement
    0.54
    Activations Density 5.414%

    No Known Activations