© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2269
    Prev
    Next
    INDEX
    Explanations

    content-agnostic function words

    oai_token-act-pair · gemini-2.0-flash

    pronouns and auxiliary verbs

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

    common words

    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
     ་་
    -0.74
     estekak
    -0.73
     grà
    -0.69
    ^(@)
    -0.67
    @[+][
    -0.63
     ISTAT
    -0.63
     AspNetCore
    -0.62
    ')";
    -0.61
    Vidite
    -0.60
     ⁠
    -0.59
    POSITIVE LOGITS
     is
    0.87
     they
    0.74
     we
    0.69
     does
    0.68
     has
    0.67
     was
    0.66
     it
    0.64
     appears
    0.63
     you
    0.63
     the
    0.60
    Activations Density 16.422%

    No Known Activations