© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1907
    Prev
    Next
    INDEX
    Explanations

    first person possessive pronouns and adjectives, sometimes in combination with verbs for emphasis

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     lives
    -1.90
     LIVES
    -1.69
     bodies
    -1.53
    lives
    -1.53
     Lives
    -1.52
     minds
    -1.50
     heads
    -1.49
     mouths
    -1.47
     vidas
    -1.45
     hearts
    -1.41
    POSITIVE LOGITS
     yourself
    0.61
    URLException
    0.60
    #+#
    0.55
    multer
    0.54
    bere
    0.54
    kháu
    0.54
    laşı
    0.54
    getExtras
    0.52
    PickerController
    0.52
     herself
    0.52
    Activations Density 6.170%

    No Known Activations