© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11440
    Prev
    Next
    INDEX
    Explanations

    phrases expressing requirements, absence, and lack of knowledge or formality.

    oai_token-act-pair · gemini-2.0-flash

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    OrBuilder
    -0.60
     estimés
    -0.57
    }]
    -0.57
    FormBuilder
    -0.57
    }],
    -0.54
    quartered
    -0.54
    }]);
    -0.53
    FXML
    -0.53
    enterOuterAlt
    -0.53
    transQ
    -0.52
    POSITIVE LOGITS
    tonsoft
    0.52
    ContentAsync
    0.50
    ulipas
    0.50
    ❮
    0.49
    imanapun
    0.49
     Administrativna
    0.49
    IMENT
    0.47
     సౌకర్య
    0.46
     slavery
    0.46
    cuda
    0.46
    Activations Density 0.350%

    No Known Activations