© 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. 6585
    Prev
    Next
    INDEX
    Explanations

    multiple present tense verbs and related keywords within a single sentence.

    oai_token-act-pair · gemini-2.0-flash

    "them"

    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
    CppMethod
    -0.66
     hän
    -0.64
     kanyang
    -0.61
    endpush
    -0.60
     protoimpl
    -0.58
    __*/
    -0.55
    #+#
    -0.54
     Lordships
    -0.53
     يتيمه
    -0.53
     flesta
    -0.52
    POSITIVE LOGITS
     them
    3.45
    them
    2.39
     THEM
    1.95
     них
    1.73
     ellos
    1.71
     Them
    1.58
     ними
    1.47
     ihnen
    1.46
     ellas
    1.46
     mereka
    1.45
    Activations Density 5.505%

    No Known Activations