© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6498
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people and companies along with their titles such as "said", "officer", "chairman", or "president".

    oai_token-act-pair · gemini-2.0-flash

    Dialogue or reported speech

    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
    uxxxx
    -0.43
     commander
    -0.41
    onshire
    -0.40
     cà
    -0.37
    Site
    -0.36
    rubin
    -0.35
    ┃
    -0.35
     Vert
    -0.35
    стави
    -0.35
    mtd
    -0.35
    POSITIVE LOGITS
    tagHelperRunner
    0.85
    MethodManager
    0.79
    UnusedPrivate
    0.77
    ArgsConstructor
    0.72
    exitRule
    0.70
    HomeAsUpEnabled
    0.70
    Tikang
    0.67
     بيها
    0.66
    StoryboardSegue
    0.65
     خارجية
    0.64
    Activations Density 1.751%

    No Known Activations