© 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. 2373
    Prev
    Next
    INDEX
    Explanations

    symbols for currency next to numbers

    oai_token-act-pair · gemini-2.0-flash

    technical or financial terminology

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

    Prices and percentages

    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
    cokinetic
    -0.56
    braucher
    -0.52
     مخطط
    -0.51
     ©️
    -0.51
     Crusoe
    -0.49
     Scholarships
    -0.49
     Oggi
    -0.49
     Assyrian
    -0.48
    }());
    -0.48
    mbic
    -0.48
    POSITIVE LOGITS
     protoimpl
    0.79
    EDEFAULT
    0.65
     FetchType
    0.57
    -£
    0.55
    showConfirm
    0.54
    клопе
    0.54
     ivelany
    0.54
    RenderAtEndOf
    0.53
     Band
    0.51
    IVAN
    0.50
    Activations Density 0.849%

    No Known Activations