© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6285
    Prev
    Next
    INDEX
    Explanations

    terms for chemical substances, especially acids and other compounds used in a lab

    oai_token-act-pair · gemini-2.0-flash

    chemical/scientific substances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    цездатний
    -0.76
     المعيارى
    -0.66
     NDEBUG
    -0.64
    évaluateur
    -0.62
    Билгалдахарш
    -0.60
     tartalomajánló
    -0.60
    ształ
    -0.59
     fathoms
    -0.59
    Ծանոթ
    -0.59
    swept
    -0.57
    POSITIVE LOGITS
    (&:
    0.52
     p
    0.49
     pem
    0.48
     prochains
    0.47
     pra
    0.45
     die
    0.44
     pol
    0.44
    новниш
    0.42
     đ
    0.42
     Die
    0.42
    Activations Density 1.941%

    No Known Activations