© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15434
    Prev
    Next
    INDEX
    Explanations

    descriptions of diverse and empowered female characters/people

    oai_token-act-pair · gemini-2.0-flash

    positive reviews of characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ]._
    -0.67
    )._
    -0.50
     pertin
    -0.48
     constru
    -0.46
    }}}}
    -0.45
    λέον
    -0.45
    "}>
    -0.45
     par
    -0.45
    Cary
    -0.43
    Carriera
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.79
    principalColumn
    0.73
    ResponseWriter
    0.60
    GEBURTSDATUM
    0.58
     épis
    0.57
    minecraftforge
    0.56
     fermée
    0.55
     économies
    0.55
     oublier
    0.54
    RegistryLite
    0.53
    Activations Density 4.007%

    No Known Activations