© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1396
    Prev
    Next
    INDEX
    Explanations

    passages that discuss chemistry or chemical processes

    oai_token-act-pair · gemini-2.0-flash

    chemical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    دانشنامهٔ
    -0.59
    役
    -0.54
    HtmlAttribute
    -0.52
     Incomplete
    -0.52
    SourceChecksum
    -0.51
     BUREAU
    -0.50
    disambiguation
    -0.49
    MultipartFile
    -0.48
     Perfor
    -0.47
     lomba
    -0.47
    POSITIVE LOGITS
    +#+#
    0.60
     représ
    0.60
    DataAnnotations
    0.58
     représenté
    0.57
     برانيه
    0.53
     reaſon
    0.53
     ſee
    0.53
     trainer
    0.52
     firſt
    0.52
     ſtate
    0.50
    Activations Density 4.746%

    No Known Activations