© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3410
    Prev
    Next
    INDEX
    Explanations

    conjunctions, prepositions, and separators adjacent to other words

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash

    and Method used: 4 — top activating texts show conjunction/list continuations, so "and"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    descent
    -0.59
    enumi
    -0.57
     gg
    -0.56
     Perrin
    -0.56
    ?}",
    -0.56
     fec
    -0.56
    ON
    -0.56
    ArgsConstructor
    -0.53
    cracker
    -0.53
     Fus
    -0.53
    POSITIVE LOGITS
     U
    0.69
    NamedQueries
    0.68
     on
    0.68
     exécu
    0.67
    principalTable
    0.66
     rése
    0.65
     noastre
    0.65
     varandra
    0.64
    <bos>
    0.63
     avoient
    0.62
    Activations Density 2.453%

    No Known Activations