© 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. 15924
    Prev
    Next
    INDEX
    Explanations

    mentions of currency, companies, government entities, or legal issues

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    ,
    -0.47
     toque
    -0.47
    花板
    -0.44
    チュ
    -0.44
     connexes
    -0.44
    接触
    -0.42
    ousand
    -0.41
     ronda
    -0.41
     mr
    -0.41
    消化
    -0.41
    POSITIVE LOGITS
    存于互联网档案馆
    0.80
    Tikang
    0.76
    +#+#
    0.73
     defaultstate
    0.72
    providedIn
    0.71
    GraphicsUnit
    0.68
    出版年
    0.67
    Sucesor
    0.66
    elemField
    0.66
     AttributeSet
    0.63
    Activations Density 20.807%

    No Known Activations