© 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. 7711
    Prev
    Next
    INDEX
    Explanations

    mentions of the material metal or of food ingredients or restaurant settings

    oai_token-act-pair · gemini-2.0-flash

    references to metal and plastic

    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
    новништво
    -0.52
    __*/
    -0.50
     wood
    -0.48
     wooden
    -0.47
     Abandon
    -0.46
     aluminium
    -0.46
     glass
    -0.45
    çait
    -0.45
     hout
    -0.45
    sapp
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.72
     متعلقه
    0.71
     مشين
    0.61
    NamedQueries
    0.61
    SpringBootTest
    0.60
     postIndex
    0.59
    примеча
    0.58
    endix
    0.56
    Бахар
    0.56
    })^
    0.56
    Activations Density 2.600%

    No Known Activations