© 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. 6261
    Prev
    Next
    INDEX
    Explanations

    words ending in "mer" and "ger", and various other random words

    oai_token-act-pair · 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
    er
    -0.60
    🏻
    -0.58
    ered
    -0.56
    SequentialGroup
    -0.56
    ibatis
    -0.55
    postIndex
    -0.54
    NameInMap
    -0.52
    🏼
    -0.50
     plomo
    -0.50
    ería
    -0.49
    POSITIVE LOGITS
    per
    0.88
    Per
    0.79
    ger
    0.75
    PER
    0.72
    mer
    0.69
     typelib
    0.68
    setVerticalGroup
    0.67
    ver
    0.65
     Per
    0.64
     per
    0.64
    Activations Density 2.097%

    No Known Activations