© 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. 4462
    Prev
    Next
    INDEX
    Explanations

    the word fragment 'fin'

    oai_token-act-pair · gemini-2.0-flash

    fin

    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
    queryInterface
    -0.61
    قایناق‌لار
    -0.59
     OFDb
    -0.58
    ividual
    -0.56
    envolvimento
    -0.55
    resas
    -0.54
    rofl
    -0.54
    Còn
    -0.54
     transférez
    -0.54
    WithIOException
    -0.54
    POSITIVE LOGITS
    expandindo
    0.56
    oneofs
    0.48
     AVER
    0.48
    enderror
    0.48
    rolid
    0.47
     autorytatywna
    0.46
    protoc
    0.46
     surla
    0.46
     JUDGE
    0.46
     judge
    0.45
    Activations Density 0.663%

    No Known Activations