© 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. 4100
    Prev
    Next
    INDEX
    Explanations

    mentions of places, systems and locations including subway station names and web server stack phrases.

    oai_token-act-pair · gemini-2.0-flash

    Multilingual, technical texts

    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
     a
    -0.71
     an
    -0.71
     this
    -0.59
     its
    -0.59
     our
    -0.53
     the
    -0.52
     my
    -0.51
     his
    -0.47
     any
    -0.46
     it
    -0.46
    POSITIVE LOGITS
     itſelf
    1.05
     myſelf
    0.98
     Shakspeare
    0.96
     Monfieur
    0.96
     themſelves
    0.95
     Majefty
    0.95
     pleaſure
    0.94
     Мексичка
    0.94
     ſind
    0.93
     ſche
    0.93
    Activations Density 0.977%

    No Known Activations