© 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. 14101
    Prev
    Next
    INDEX
    Explanations

    a mixture of acronyms representing organizations or concepts as well as chemical elements

    oai_token-act-pair · gemini-2.0-flash

    N

    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
     BB
    -0.49
     BE
    -0.48
     DC
    -0.48
     TE
    -0.47
     DE
    -0.46
     PL
    -0.45
     RR
    -0.45
     SH
    -0.45
     HE
    -0.44
     DB
    -0.44
    POSITIVE LOGITS
    ATORS
    0.69
    ATURA
    0.66
    IALS
    0.65
    ATOS
    0.64
    ATIVES
    0.63
    ILLS
    0.63
    ANGER
    0.63
    bukkit
    0.62
    ators
    0.62
    ANKS
    0.61
    Activations Density 6.110%

    No Known Activations