© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 15223
    Prev
    Next
    INDEX
    Explanations

    general words related to technology and also possible proper nouns

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash

    French adjectives

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    .";
    
    -1.24
    ?";
    -1.20
    ."]
    -1.17
    "));
    
    -1.16
    ...',
    -1.13
    ?");
    -1.13
    **:
    -1.12
    ...",
    -1.12
    ?',
    -1.12
    `;
    
    -1.12
    POSITIVE LOGITS
     secondaires
    0.65
    ÓS
    0.64
     malheureux
    0.64
     aveug
    0.60
     automatiques
    0.60
     quæ
    0.60
     intermédiaire
    0.60
    İY
    0.59
     étrangère
    0.59
     heureuse
    0.59
    Activations Density 16.891%

    No Known Activations