© 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. 12017
    Prev
    Next
    INDEX
    Explanations

    fragments of programming code that signify warnings, errors, or invalid states

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    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
    .
    -0.47
     tỏ
    -0.42
    nitř
    -0.41
    pil
    -0.39
    !
    -0.38
     schon
    -0.38
    kov
    -0.38
     vieux
    -0.37
    <bos>
    -0.36
    یش
    -0.36
    POSITIVE LOGITS
     autorytatywna
    0.91
    OGND
    0.89
     pleaſure
    0.72
    NOPQRST
    0.71
    PreferredItem
    0.71
     Wikimedijinoj
    0.71
     ComVisible
    0.68
    <()>
    0.67
    fjspx
    0.67
     purpoſe
    0.66
    Activations Density 0.299%

    No Known Activations