© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10433
    Prev
    Next
    INDEX
    Explanations

    mentions of people, especially men or groups of people

    oai_token-act-pair · gemini-2.0-flash

    men

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     oprot
    -0.68
     Roskov
    -0.67
     '/':
    -0.53
    ieras
    -0.53
    fromnode
    -0.51
    ี่
    -0.48
    lyk
    -0.48
     LING
    -0.48
    setVerticalGroup
    -0.47
    hlungen
    -0.47
    POSITIVE LOGITS
    <bos>
    1.95
    Бахар
    0.58
    esez
    0.52
    '
    0.51
     personne
    0.50
     invokingState
    0.48
    principalTable
    0.48
    engertian
    0.47
    ’
    0.47
     berdua
    0.47
    Activations Density 0.391%

    No Known Activations