© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5203
    Prev
    Next
    INDEX
    Explanations

    the word "lost"

    oai_token-act-pair · gemini-2.0-flash

    lost

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    MessageOf
    -0.82
     "..\..\..\
    -0.71
    enterOuterAlt
    -0.67
     متعلقه
    -0.65
     Roskov
    -0.64
    :✨
    -0.62
    DeleteBehavior
    -0.62
    protoimpl
    -0.60
     Bioaccumulative
    -0.60
    oneofs
    -0.59
    POSITIVE LOGITS
    ʖ
    0.45
    værk
    0.43
     légale
    0.43
    ptonshire
    0.43
    wykle
    0.41
    >[]
    0.40
    stående
    0.40
    țiunea
    0.40
    parency
    0.40
    Contenu
    0.40
    Activations Density 0.699%

    No Known Activations