© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12467
    Prev
    Next
    INDEX
    Explanations

    words which may be proper nouns, especially company and product names.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    enumi
    -0.47
    soni
    -0.43
    ு
    -0.43
     consultato
    -0.43
    lo
    -0.43
     sel
    -0.43
    fR
    -0.42
     describing
    -0.42
     ihrer
    -0.42
    קת
    -0.41
    POSITIVE LOGITS
    évaluateur
    0.94
    rrggbb
    0.91
    цездатний
    0.89
     gynhyrchwyd
    0.88
     ujednoznacz
    0.86
    webElementXpaths
    0.86
    SharedDtor
    0.79
     myſelf
    0.78
    NameInMap
    0.78
     purpoſe
    0.77
    Activations Density 4.422%

    No Known Activations