© 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. 2594
    Prev
    Next
    INDEX
    Explanations

    quantities and descriptive words, possibly within discussions of social issues

    oai_token-act-pair · gemini-2.0-flash

    say "of"

    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
    ^(@)
    -1.03
     ſtate
    -0.99
     faſt
    -0.98
     Anſ
    -0.98
     ſeveral
    -0.97
     pleaſure
    -0.97
     Reſ
    -0.96
     Efq
    -0.94
     reaſon
    -0.93
     houſe
    -0.93
    POSITIVE LOGITS
    0
    0.64
    1
    0.59
    5
    0.57
    2
    0.57
    4
    0.53
    9
    0.51
    7
    0.51
    3
    0.50
     -
    0.49
    </i>
    0.49
    Activations Density 9.734%

    No Known Activations