Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14342
    Prev
    Next
    INDEX
    Explanations

    scientific studies related to hormones and sexual attraction

    oai_token-act-pair · gemini-2.0-flash

    Numerical values

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -0.90
    TagMode
    -0.81
    ArgsConstructor
    -0.80
     tartalomajánló
    -0.75
     lèvres
    -0.75
    berdayakan
    -0.73
    RegressionTest
    -0.73
    Geplaatst
    -0.72
     Anſ
    -0.71
     myſelf
    -0.69
    POSITIVE LOGITS
     levels
    1.79
    levels
    1.42
     Levels
    1.38
     LEVELS
    1.33
    Levels
    1.25
     rates
    1.23
     figures
    1.13
     numbers
    1.04
     niveles
    0.93
     prices
    0.91
    Activations Density 3.115%

    No Known Activations