© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6949
    Prev
    Next
    INDEX
    Explanations

    words related to people experiencing hardship and injustice particularly related to war, ethnicity, or legal issues

    oai_token-act-pair · gemini-2.0-flash

    female pronouns

    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
     okuyayım
    -0.77
    ньому
    -0.75
     оно
    -0.65
     яке
    -0.65
     которое
    -0.65
     Оно
    -0.56
    Билгалдахарш
    -0.54
     quelli
    -0.54
    bkz
    -0.54
    quels
    -0.52
    POSITIVE LOGITS
     her
    4.53
    her
    3.11
     she
    2.92
     herself
    2.67
     hers
    2.61
    彼女の
    2.61
     그녀
    2.55
    她的
    2.52
    Her
    2.45
     hennes
    2.42
    Activations Density 26.882%

    No Known Activations