© 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. 2489
    Prev
    Next
    INDEX
    Explanations

    things that are metaphors or literal objects made of stone or gold

    oai_token-act-pair · gemini-2.0-flash

    materials and elements

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

    materials

    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
     fiscale
    -0.45
     cottura
    -0.44
    ęt
    -0.44
    SpringBootTest
    -0.41
    lewati
    -0.41
     aveug
    -0.40
    unanje
    -0.40
     dabei
    -0.39
     nướng
    -0.38
     comenz
    -0.37
    POSITIVE LOGITS
     gold
    1.27
     wood
    1.23
     steel
    1.22
     metal
    1.20
     stone
    1.12
     glass
    1.10
    gold
    1.10
     bronze
    1.05
     brass
    1.04
     aluminum
    1.03
    Activations Density 2.493%

    No Known Activations