© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4609
    Prev
    Next
    INDEX
    Explanations

    URLs related to code repositories and video websites, specifically GitHub and YouTube

    oai_token-act-pair · gemini-2.0-flash

    github or youtube

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    CP
    -0.41
    Cam
    -0.40
    Tin
    -0.38
    CC
    -0.37
    Ts
    -0.35
    __(/*!
    -0.35
    Com
    -0.35
    Cl
    -0.34
    ECO
    -0.33
    ERT
    -0.33
    POSITIVE LOGITS
    twimg
    0.82
     تانيه
    0.71
    testify
    0.68
    saraba
    0.67
     ddelweddau
    0.64
     autorytatywna
    0.62
    AnchorStyles
    0.59
    SourceChecksum
    0.59
     Audiodateien
    0.59
    kpop
    0.58
    Activations Density 6.008%

    No Known Activations