© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4315
    Prev
    Next
    INDEX
    Explanations

    references to people and groups

    oai_token-act-pair · gemini-2.0-flash

    people

    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
     that
    -2.14
    that
    -1.60
     bahwa
    -1.31
     bahawa
    -1.18
     kwamba
    -1.11
    That
    -1.09
     dass
    -1.08
     That
    -1.08
     rằng
    -1.06
    THAT
    -1.04
    POSITIVE LOGITS
     who
    0.77
    styrelsen
    0.62
    Revenir
    0.58
     Vikipedi
    0.46
     quem
    0.45
    ندگان
    0.44
    Who
    0.41
    sterne
    0.41
    \
    0.41
     ч
    0.40
    Activations Density 2.415%

    No Known Activations