© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14546
    Prev
    Next
    INDEX
    Explanations

    instances of common words, especially 'all', 'the', 'our', 'and', 'for', next' also a few random nouns like "Symphony", "feelings", "years", "months"

    oai_token-act-pair · gemini-2.0-flash

    our

    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
    ArrowToggle
    -0.55
    ofire
    -0.53
    numerusform
    -0.51
    PhysRevLett
    -0.50
     Puntos
    -0.49
    enlace
    -0.48
     prezzo
    -0.46
    endforeach
    -0.45
    cVar
    -0.45
     Larsson
    -0.45
    POSITIVE LOGITS
    RuleContext
    0.61
    #!/
    0.58
     precies
    0.57
    FunctionFlags
    0.54
    ABULARY
    0.53
    صحاب
    0.53
     MAIL
    0.51
    RectangleBorder
    0.51
    ardless
    0.51
    saraba
    0.51
    Activations Density 5.927%

    No Known Activations