© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4276
    Prev
    Next
    INDEX
    Explanations

    the name Robert and sometimes other names and modifying adjectives

    oai_token-act-pair · gemini-2.0-flash

    Robert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Robert
    -1.82
    Robert
    -1.71
     ROBERT
    -1.46
     robert
    -1.40
     Rob
    -1.29
    ROBERT
    -1.27
     Bob
    -1.23
    Bob
    -1.14
    Rob
    -1.13
     Роб
    -1.07
    POSITIVE LOGITS
     مرئيه
    0.72
    ReusableCell
    0.59
     Penh
    0.55
     imperialism
    0.53
     ArrayAdapter
    0.53
    zbęd
    0.52
     /\.
    0.52
    Revenir
    0.52
    InstanceState
    0.52
    vernight
    0.50
    Activations Density 4.944%

    No Known Activations