© 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. 14818
    Prev
    Next
    INDEX
    Explanations

    words or phrases that often appear with other particular words, as if the neuron is completing a sentence

    oai_token-act-pair · gemini-2.0-flash

    are

    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
    DoubleQuotes
    -0.75
     يتيمه
    -0.63
     Są
    -0.62
     oprot
    -0.62
     yere
    -0.61
     propOrder
    -0.59
     gratuitement
    -0.58
     are
    -0.57
    localctx
    -0.57
    évaluateur
    -0.57
    POSITIVE LOGITS
    __':
    0.53
     web
    0.53
    swt
    0.48
    __":
    0.47
    gesteld
    0.47
     giacca
    0.45
    ÍN
    0.44
    AILABLE
    0.43
    __':
    0.43
    homonymie
    0.43
    Activations Density 20.198%

    No Known Activations