© 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
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 13591
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe a location or building

    oai_token-act-pair · gemini-2.0-flash

    describing location or construction

    np_max-act · gemini-2.0-flash

    past-tense verbs (past participles)

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    rrggbb
    -0.75
     Vichy
    -0.60
    Active
    -0.59
     attivo
    -0.59
     aktive
    -0.59
     Athenian
    -0.59
    ACTIVE
    -0.59
     actives
    -0.58
     actif
    -0.58
     Allegretto
    -0.58
    POSITIVE LOGITS
    ]');
    0.65
    }}^
    0.65
    ]$}
    0.61
    */;
    0.60
    тельностью
    0.60
    >`;
    0.60
    </caption>
    0.59
    "],
    
    0.59
     }}"
    0.58
    ()");
    0.56
    Activations Density 1.748%

    No Known Activations