© 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. 13501
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to instructions and technical documentation

    oai_token-act-pair · gemini-2.0-flash

    instructions and guidance

    np_max-act · 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
    abord
    -0.49
     technique
    -0.43
    azole
    -0.41
     estan
    -0.40
     do
    -0.40
    endiri
    -0.39
     Preferencias
    -0.38
     method
    -0.38
     particuli
    -0.38
    是如何
    -0.38
    POSITIVE LOGITS
    ApiModelProperty
    0.83
    
    0.79
    bootstrapcdn
    0.77
    Portale
    0.73
    ValueStyle
    0.66
    脚注の使い方
    0.66
     Administrativna
    0.66
    OGND
    0.64
     GenerationType
    0.63
    Ecotoxicity
    0.63
    Activations Density 1.971%

    No Known Activations