© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15623
    Prev
    Next
    INDEX
    Explanations

    non-English letters and symbols and IRC chatter

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    LookAnd
    -0.73
    ftagPool
    -0.72
    ſhip
    -0.70
    olesale
    -0.66
     esternos
    -0.65
    RTDA
    -0.64
     Monfieur
    -0.64
     gynhyrchwyd
    -0.64
    =$?
    -0.63
    virons
    -0.63
    POSITIVE LOGITS
    •
    0.60
    β
    0.59
    ©
    0.57
    α
    0.56
    ®
    0.54
    ¬
    0.54
    ^
    0.54
    ·
    0.53
    �
    0.53
    à
    0.53
    Activations Density 7.827%

    No Known Activations