© 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. 9203
    Prev
    Next
    INDEX
    Explanations

    a variety of statistical and logical words plus numbers

    oai_token-act-pair · gemini-2.0-flash

    say "w"

    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
    </tfoot>
    -0.66
     fédéral
    -0.60
     przód
    -0.58
    日閲覧
    -0.57
    MergeFrom
    -0.56
    łbym
    -0.56
     InputDecoration
    -0.55
     TextInputType
    -0.55
     dieß
    -0.55
    kijken
    -0.55
    POSITIVE LOGITS
     w
    2.41
     W
    2.03
    W
    1.76
    w
    1.70
     wh
    1.66
     wa
    1.56
     wi
    1.53
     WH
    1.53
    Ｗ
    1.38
    WH
    1.34
    Activations Density 7.550%

    No Known Activations