© 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. 15583
    Prev
    Next
    INDEX
    Explanations

    words related to function or specification in product descriptions

    oai_token-act-pair · gemini-2.0-flash

    product features

    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
    fromnode
    -0.65
     corrector
    -0.63
     Playboy
    -0.58
    obus
    -0.56
     tartalomajánló
    -0.56
     houſe
    -0.55
    EndInit
    -0.54
     препратки
    -0.54
    zedł
    -0.53
     divisible
    -0.53
    POSITIVE LOGITS
     مشين
    0.64
    principalTable
    0.64
    twimg
    0.63
     שוליים
    0.51
    Gdx
    0.47
     Roskov
    0.46
    AutoField
    0.45
     архивлан
    0.44
    enumi
    0.43
    ""}
    0.43
    Activations Density 1.883%

    No Known Activations