© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5139
    Prev
    Next
    INDEX
    Explanations

    words that are prepositions and numbers

    oai_token-act-pair · gemini-2.0-flash

    identifiers or code-like terms

    np_token-act-pair-logits · gpt-4o-mini

    time periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     twenty
    -0.68
     thirty
    -0.65
    twenty
    -0.63
    Twenty
    -0.61
     Twenty
    -0.61
     مشين
    -0.61
     vingt
    -0.58
     Thirty
    -0.56
     fifteen
    -0.54
    Thirty
    -0.52
    POSITIVE LOGITS
    tagHelperRunner
    0.81
    MessageTagHelper
    0.64
    rrggbb
    0.63
    #+#
    0.62
    DebuggerNonUser
    0.61
     GenerationType
    0.58
    Autoritní
    0.57
    igshid
    0.57
    ChildScrollView
    0.56
    LLocation
    0.55
    Activations Density 1.158%

    No Known Activations