© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6820
    Prev
    Next
    INDEX
    Explanations

    academic articles and presentations, especially sections relating to data collection and analysis, supporting information, and acknowledgements.

    oai_token-act-pair · gemini-2.0-flash

    supplementary information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     this
    -0.79
    this
    -0.74
     these
    -0.70
    these
    -0.62
     any
    -0.59
    any
    -0.56
     some
    -0.51
     each
    -0.51
    myself
    -0.50
     our
    -0.50
    POSITIVE LOGITS
    >{@
    0.66
    \}\\
    0.65
    ThroughAttribute
    0.60
    出版年
    0.57
    FieldBuilder
    0.57
    日閲覧
    0.56
     contained
    0.55
    AndroidJUnit
    0.55
    Tikang
    0.54
     kasarigan
    0.54
    Activations Density 37.880%

    No Known Activations