© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9644
    Prev
    Next
    INDEX
    Explanations

    word fragments, especially those in Femalefirst and Danish words with accented characters.

    oai_token-act-pair · gemini-2.0-flash

    female/male

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     BrowserModule
    -0.84
     ioutil
    -0.66
     AssemblyCulture
    -0.64
     Atenas
    -0.63
    cepan
    -0.59
     [*]
    -0.59
     onCreateView
    -0.59
     []:
    -0.58
    vency
    -0.58
     ơn
    -0.58
    POSITIVE LOGITS
     female
    1.13
     women
    1.11
     male
    1.08
     Female
    1.07
    Female
    1.06
    female
    1.03
     FEMALE
    0.97
    Male
    0.96
     Women
    0.94
     females
    0.94
    Activations Density 0.295%

    No Known Activations