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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10068
    Prev
    Next
    INDEX
    Explanations

    words related to the self and interpersonal relationships, specially first and second person pronouns

    oai_token-act-pair · gemini-2.0-flash

    Possessive 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
    
    -0.79
     Signalez
    -0.75
    ChildScrollView
    -0.70
    PerformLayout
    -0.63
    rawDesc
    -0.63
    RegistryLite
    -0.57
    modb
    -0.57
    ]")]
    -0.57
    はじめに
    -0.56
    ocino
    -0.54
    POSITIVE LOGITS
     çıktı
    0.51
    si
    0.49
    loge
    0.49
     gustos
    0.49
    سام
    0.47
    üğü
    0.47
    Log
    0.46
    Affiliation
    0.45
    ritis
    0.45
    stal
    0.44
    Activations Density 11.305%

    No Known Activations