© 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. 15442
    Prev
    Next
    INDEX
    Explanations

    image references, and associated text of figure notes and captions

    oai_token-act-pair · gemini-2.0-flash

    images

    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
    ]--;
    -0.88
     kasarigan
    -0.84
     <=",
    -0.75
    contentLoaded
    -0.68
    ‘‘
    -0.67
     متعلقه
    -0.63
     >=",
    -0.63
     ModelExpression
    -0.62
     NUKAT
    -0.61
     gynhyrchwyd
    -0.58
    POSITIVE LOGITS
     visione
    0.48
    çası
    0.47
     hänen
    0.45
     getView
    0.44
    athlon
    0.44
     smtplib
    0.44
    يكب
    0.44
    oredCriteria
    0.41
    MockMvc
    0.41
    WireFormatLite
    0.41
    Activations Density 6.286%

    No Known Activations