© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6381
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to social interactions and positive relationships with others

    oai_token-act-pair · gemini-2.0-flash

    positive personal attributes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ter
    -0.50
     Mar
    -0.49
     Ste
    -0.48
     
    -0.48
    net
    -0.48
     bre
    -0.46
     hard
    -0.44
     No
    -0.44
     ter
    -0.44
    Busy
    -0.43
    POSITIVE LOGITS
     Theſe
    1.04
     myſelf
    0.98
     Anſ
    0.89
    MigrationBuilder
    0.86
    dymyr
    0.86
     beginnetje
    0.86
    Personendaten
    0.85
     itſelf
    0.85
     Monfieur
    0.84
     '\\;'
    0.83
    Activations Density 1.353%

    No Known Activations