© 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. 12578
    Prev
    Next
    INDEX
    Explanations

    superlative comparisons.

    oai_token-act-pair · gemini-2.0-flash

    Exceeding expectations

    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
     own
    -0.49
    具
    -0.46
     first
    -0.45
     تانيه
    -0.44
     other
    -0.44
    ded
    -0.42
     second
    -0.42
    гер
    -0.42
    sidemargin
    -0.42
    yse
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.82
    +#+#
    0.68
    DockStyle
    0.64
    شهاد
    0.63
    +:+
    0.63
     publiques
    0.61
    seamnă
    0.61
    脚注の使い方
    0.60
     estekak
    0.60
     morire
    0.59
    Activations Density 0.199%

    No Known Activations