© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15391
    Prev
    Next
    INDEX
    Explanations

    the word "saving"

    oai_token-act-pair · gemini-2.0-flash

    saving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    发表于
    -0.85
    #+#
    -0.82
    httphttps
    -0.78
     fermés
    -0.77
     communs
    -0.76
    cessite
    -0.71
    \{\\
    -0.71
     dépos
    -0.69
    BeginInit
    -0.69
    EndInit
    -0.67
    POSITIVE LOGITS
     Hera
    0.55
    edith
    0.54
    ?")
    0.53
     disponer
    0.53
    +')
    0.52
     yyr
    0.52
    Captor
    0.51
     diete
    0.50
     Euchar
    0.50
     Damit
    0.50
    Activations Density 0.815%

    No Known Activations