© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3207
    Prev
    Next
    INDEX
    Explanations

    a mix of political figures and references, mathematical symbols, URLs, code snippets, or other structured data

    oai_token-act-pair · gemini-2.0-flash

    beginnings and endings

    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
    y
    -0.59
    ya
    -0.42
    q
    -0.35
    que
    -0.34
    yad
    -0.34
    ye
    -0.33
    éri
    -0.32
    ke
    -0.32
    ow
    -0.32
    ka
    -0.32
    POSITIVE LOGITS
    PerformLayout
    1.00
     pleaſure
    0.94
    ValueStyle
    0.91
     raiſ
    0.86
     myſelf
    0.83
     ſtate
    0.82
     itſelf
    0.81
     greateſt
    0.79
     poffible
    0.79
     Reſ
    0.78
    Activations Density 15.635%

    No Known Activations