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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6660
    Prev
    Next
    INDEX
    Explanations

    the word "hat" or pronouns referring to a female

    oai_token-act-pair · gemini-2.0-flash

    hat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Majefty
    -0.63
    ly
    -0.63
     vicini
    -0.62
     ['$
    -0.60
     تضيفلها
    -0.60
     suivants
    -0.60
     affinch
    -0.60
    webElementXpaths
    -0.59
     يتيمه
    -0.59
     auroit
    -0.59
    POSITIVE LOGITS
    OSPH
    0.68
     مصرى
    0.66
    inderung
    0.66
     بيها
    0.63
    quarie
    0.62
     Donahue
    0.61
     podjela
    0.59
    BERGER
    0.59
    icach
    0.58
    salty
    0.58
    Activations Density 2.557%

    No Known Activations