© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13413
    Prev
    Next
    INDEX
    Explanations

    capital letters adjacent to lower case letters, especially in the middle of words or names

    oai_token-act-pair · gemini-2.0-flash

    L

    np_max-act-logits · gemini-2.0-flash
    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
    escalier
    -0.54
    hébergement
    -0.52
    étranger
    -0.52
    amitié
    -0.49
    entraînement
    -0.48
    extérieur
    -0.48
    hygiène
    -0.47
    humanité
    -0.46
    étape
    -0.46
    élaboration
    -0.45
    POSITIVE LOGITS
    ailing
    0.50
    enser
    0.49
    iress
    0.47
    essions
    0.45
    owel
    0.45
    osing
    0.45
    oken
    0.45
    iint
    0.43
    ocument
    0.43
    angering
    0.43
    Activations Density 18.717%

    No Known Activations