© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16106
    Prev
    Next
    INDEX
    Explanations

    words relating to family relationships

    oai_token-act-pair · gemini-2.0-flash

    Family members

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ScopeManager
    -0.59
    AccessorTable
    -0.54
     Picchu
    -0.51
     pare
    -0.50
     vian
    -0.50
    uxxxx
    -0.50
     חיצוניים
    -0.48
    󠁮
    -0.47
    Tämä
    -0.47
     Normdatei
    -0.46
    POSITIVE LOGITS
     GenerationType
    0.74
    httphttps
    0.63
     antics
    0.58
    rrggbb
    0.54
     "..\..\..\
    0.54
    ArgsConstructor
    0.51
     comigo
    0.50
     lumineux
    0.49
    manteau
    0.49
     überweisen
    0.48
    Activations Density 1.672%

    No Known Activations