© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10011
    Prev
    Next
    INDEX
    Explanations

    words that describe negative opinions or behaviors

    oai_token-act-pair · gemini-2.0-flash

    criticism, negativity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     يتيمه
    -0.60
    ğraf
    -0.55
     <>",
    -0.54
    FormTagHelper
    -0.53
    DDE
    -0.50
    ிக்க
    -0.49
     beginnetje
    -0.49
     AppCompatTheme
    -0.48
     beteken
    -0.48
    resave
    -0.47
    POSITIVE LOGITS
    يميديا
    0.72
     TextInputType
    0.65
    olkata
    0.58
     Molière
    0.58
    AutoSize
    0.57
     MonoBehaviour
    0.57
    Viited
    0.56
    tinyos
    0.56
     namin
    0.56
     critics
    0.55
    Activations Density 0.756%

    No Known Activations