© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12762
    Prev
    Next
    INDEX
    Explanations

    words related to societal hierarchy, shame, and powerlessness

    oai_token-act-pair · gemini-2.0-flash

    clerk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.65
     فريبيس
    -0.63
    gonic
    -0.59
     hereof
    -0.57
    ldorf
    -0.56
    }.
    -0.56
    AndroidJUnit
    -0.56
     NUKAT
    -0.55
    ($__
    -0.54
    rifugal
    -0.54
    POSITIVE LOGITS
    ########.
    0.66
    月号
    0.50
     senaste
    0.46
    직
    0.46
     pacchetto
    0.45
    RegressionTest
    0.45
    featureID
    0.44
     instalar
    0.44
    enskap
    0.43
     importanza
    0.43
    Activations Density 0.245%

    No Known Activations