© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12400
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of sentences or question/exclamations

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     des
    -0.52
     de
    -0.51
    TAWA
    -0.49
    .
    -0.48
     p
    -0.45
     su
    -0.45
     k
    -0.45
     she
    -0.45
     sol
    -0.43
    '
    -0.43
    POSITIVE LOGITS
     Monfieur
    0.92
     Diſ
    0.90
     itſelf
    0.90
     pleaſure
    0.88
     myſelf
    0.87
    saraba
    0.86
     purpoſe
    0.83
     Jefus
    0.81
     ―――――
    0.80
     raiſ
    0.80
    Activations Density 1.123%

    No Known Activations