© 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. 6476
    Prev
    Next
    INDEX
    Explanations

    a mountain range in New York called Helderberg

    oai_token-act-pair · gemini-2.0-flash

    location names

    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
    الث
    -0.47
     Judah
    -0.47
    Baca
    -0.47
     đồ
    -0.46
    SharedCtor
    -0.46
     OnInit
    -0.45
    ukų
    -0.45
    isia
    -0.45
     South
    -0.45
     lacking
    -0.44
    POSITIVE LOGITS
     "}";
    0.65
    PyExc
    0.65
    yntaxException
    0.59
    ."));
    0.57
    recovered
    0.54
    styleType
    0.54
    sending
    0.53
    oyl
    0.53
     ExecuteAsync
    0.52
    uxxxx
    0.52
    Activations Density 0.046%

    No Known Activations