© 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. 3507
    Prev
    Next
    INDEX
    Explanations

    phrases using words like "far", "more", "much", and "a lot".

    oai_token-act-pair · gemini-2.0-flash

    games of chance

    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
    SourceChecksum
    -0.72
     незавершена
    -0.62
     referenties
    -0.57
    UnusedPrivate
    -0.57
    تقاوى
    -0.56
     TextAlign
    -0.54
    országban
    -0.53
    ("'"
    -0.52
    FieldDescriptor
    -0.52
    ValueStyle
    -0.50
    POSITIVE LOGITS
     trick
    1.16
    trick
    0.91
     risk
    0.88
     RISK
    0.81
    risk
    0.78
     Trick
    0.77
     Risk
    0.74
    Risk
    0.73
     truco
    0.68
    RISK
    0.67
    Activations Density 2.020%

    No Known Activations