© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12727
    Prev
    Next
    INDEX
    Explanations

    parts of words ending in vowels that may be prefixes and suffixes

    oai_token-act-pair · gemini-2.0-flash

    Incomplete/fragmented words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Theſe
    -1.09
    RenderAtEndOf
    -1.08
     purpoſe
    -1.04
     ſtate
    -1.02
     Monfieur
    -0.99
     theſe
    -0.98
     myſelf
    -0.96
     resourceCulture
    -0.96
     themſelves
    -0.96
    ReusableCell
    -0.93
    POSITIVE LOGITS
    ­
    0.39
    vi
    0.37
     própria
    0.37
     próprias
    0.35
    boldsymbol
    0.34
     naj
    0.34
    ant
    0.33
    ce
    0.33
    pre
    0.32
     próprio
    0.32
    Activations Density 1.037%

    No Known Activations