© 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. 13992
    Prev
    Next
    INDEX
    Explanations

    a mix of French words, cooking-related words, game/fantasy-related words and words related to the medical profession

    oai_token-act-pair · gemini-2.0-flash

    discovery and exploration

    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
     discovery
    -1.10
     discoveries
    -1.06
     discovering
    -1.04
     descubrimiento
    -1.04
     discover
    -1.02
     découverte
    -1.02
     discovered
    -1.00
    discovery
    -1.00
    discover
    -0.99
     scoperta
    -0.99
    POSITIVE LOGITS
    RTHOOK
    0.49
    諏訪
    0.45
     Ex
    0.42
     choix
    0.41
     चुनें
    0.41
    eqref
    0.41
     pukul
    0.40
    Context
    0.40
     OMITTED
    0.40
    putString
    0.40
    Activations Density 37.850%

    No Known Activations