© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6352
    Prev
    Next
    INDEX
    Explanations

    instances of first-person pronouns and statements of ability, possession, or desire

    oai_token-act-pair · gemini-2.0-flash

    auxiliary verbs

    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
     Efq
    -1.11
     itſelf
    -0.96
    ſelf
    -0.96
     $_"
    -0.95
     Majefty
    -0.95
     houſe
    -0.88
     Jefus
    -0.88
     poffe
    -0.87
     whoſe
    -0.86
     themſelves
    -0.85
    POSITIVE LOGITS
     my
    1.28
    my
    1.14
     I
    1.05
     My
    1.02
    My
    1.02
     myself
    1.01
     saya
    0.92
    我
    0.84
    我的
    0.84
     minhas
    0.84
    Activations Density 4.637%

    No Known Activations