© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14264
    Prev
    Next
    INDEX
    Explanations

    words related to "self" or things done by oneself

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     self
    -1.74
    self
    -1.67
     Self
    -1.62
    Self
    -1.60
     SELF
    -1.48
    SELF
    -1.40
    selves
    -1.34
     themselves
    -1.20
     himself
    -1.20
     selves
    -1.19
    POSITIVE LOGITS
    endphp
    0.71
     <=",
    0.61
     fVar
    0.59
     SqlDbType
    0.58
    amaño
    0.57
    DockStyle
    0.57
    ReusableCell
    0.56
    principalColumn
    0.56
    mesis
    0.55
     pageContext
    0.54
    Activations Density 0.832%

    No Known Activations