© 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. 3039
    Prev
    Next
    INDEX
    Explanations

    words that relate to oneself and potentially negative connotations about oneself

    oai_token-act-pair · gemini-2.0-flash

    self

    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
    ukone
    -0.64
    '}>
    -0.61
    __":
    -0.58
    __':
    -0.56
    rawDesc
    -0.56
    TagMode
    -0.52
     //$
    -0.50
    <bos>
    -0.49
    tements
    -0.49
     VM
    -0.49
    POSITIVE LOGITS
    oredCriteria
    0.63
     réelle
    0.58
     charité
    0.58
    MessageTagHelper
    0.57
     pédagogique
    0.57
     ragion
    0.57
     religieuse
    0.57
     garanzia
    0.56
     sûre
    0.54
     avancée
    0.54
    Activations Density 3.742%

    No Known Activations