© 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. 8926
    Prev
    Next
    INDEX
    Explanations

    words that suggest something is being requested, worked toward, or achieved

    oai_token-act-pair · gemini-2.0-flash

    Instructions and Guidelines

    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
     Efq
    -0.88
     houſe
    -0.83
     himſelf
    -0.83
     myſelf
    -0.82
     ſeveral
    -0.81
     whoſe
    -0.81
    ſelf
    -0.81
     defire
    -0.80
     becauſe
    -0.79
     pleaſure
    -0.79
    POSITIVE LOGITS
     ready
    0.54
    READY
    0.45
    Ready
    0.45
     READY
    0.45
     Ready
    0.44
     kun
    0.43
    ready
    0.42
    newBuilder
    0.42
    bisoft
    0.41
     Point
    0.41
    Activations Density 0.468%

    No Known Activations