© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6585
    Prev
    Next
    INDEX
    Explanations

    words related to medical research, especially pharmacology and cellular biology

    oai_token-act-pair · gemini-2.0-flash

    scientific/medical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ⓘ
    -0.57
    styleable
    -0.54
    IENT
    -0.51
    WebServlet
    -0.50
    AutoScaleMode
    -0.49
    enterOuterAlt
    -0.49
    balleur
    -0.49
     ๆ
    -0.47
    DebuggerNonUser
    -0.47
    ậy
    -0.47
    POSITIVE LOGITS
     Roskov
    0.63
    InstanceState
    0.58
     trattano
    0.56
     wester
    0.55
     незавершена
    0.54
     Wester
    0.54
    OrFail
    0.53
     دیکھیے
    0.52
    Wester
    0.51
    RTLD
    0.50
    Activations Density 6.027%

    No Known Activations