© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 309
    Prev
    Next
    INDEX
    Explanations

    Polish place names

    oai_token-act-pair · gemini-2.0-flash

    Polish text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     pleaſure
    -1.18
     myſelf
    -1.16
     itſelf
    -1.12
     Monfieur
    -1.09
     Majefty
    -1.09
    ſelf
    -1.05
     purpoſe
    -1.03
     Anſ
    -1.01
     themſelves
    -0.98
     raiſ
    -0.97
    POSITIVE LOGITS
    one
    0.40
     di
    0.30
    setHorizontal
    0.30
    umi
    0.29
    .
    0.28
     com
    0.28
     ce
    0.28
    ContentAsync
    0.28
    fa
    0.28
     por
    0.28
    Activations Density 0.264%

    No Known Activations