© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14936
    Prev
    Next
    INDEX
    Explanations

    words ending in "-in(e)", "-an(s)", "-on(s)", "gallate", "oid", or "ose" that relate to chemicals or biological processes.

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    liothèque
    -0.58
    Referencer
    -0.52
    Insee
    -0.49
    >{@
    -0.48
    enderror
    -0.45
    WithIOException
    -0.45
    corer
    -0.44
    MockBean
    -0.44
    EndProject
    -0.43
    MessageTagHelper
    -0.43
    POSITIVE LOGITS
     dépens
    0.59
     Shaksp
    0.58
    UserScript
    0.57
     tasche
    0.53
    chaub
    0.53
    ^(@)
    0.53
    Sprintf
    0.52
     fuo
    0.52
     betweenstory
    0.52
    WebVitals
    0.51
    Activations Density 3.825%

    No Known Activations