© 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. 12708
    Prev
    Next
    INDEX
    Explanations

    a mix of imperative verbs and words related to technology

    oai_token-act-pair · gemini-2.0-flash

    commands or suggestions

    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
     समीक्षाएं
    -0.65
     yourself
    -0.64
     yourselves
    -0.58
    Personensuche
    -0.57
    InputTagHelper
    -0.57
     gärna
    -0.56
    Rhestr
    -0.56
    fiez
    -0.54
    joit
    -0.54
    Don
    -0.54
    POSITIVE LOGITS
    HasOne
    0.58
    czyna
    0.58
    }}}{\
    0.56
     Sinon
    0.54
    Tetapi
    0.52
    ALIAN
    0.51
    LEncoder
    0.51
     Enfin
    0.50
     finally
    0.50
    --]
    0.50
    Activations Density 1.028%

    No Known Activations