© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2980
    Prev
    Next
    INDEX
    Explanations

    what looks like package or project names, and some groups of capitalized initials

    oai_token-act-pair · gemini-2.0-flash

    foreign language snippets

    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
     di
    -0.44
     
    -0.44
     de
    -0.41
     des
    -0.40
     du
    -0.38
     an
    -0.36
     y
    -0.36
     pem
    -0.36
     (
    -0.35
    .
    -0.35
    POSITIVE LOGITS
     Monfieur
    2.03
     itſelf
    2.02
     pleaſure
    1.99
     myſelf
    1.99
     purpoſe
    1.98
     houſe
    1.95
     Majefty
    1.95
     Efq
    1.94
     Houſe
    1.89
     ſeveral
    1.89
    Activations Density 7.799%

    No Known Activations