© 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. 14447
    Prev
    Next
    INDEX
    Explanations

    words with suffixes indicating a profession or a kind of person

    oai_token-act-pair · gemini-2.0-flash

    various nouns

    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
    ner
    -0.82
    ber
    -0.82
    NER
    -0.81
    iter
    -0.80
    INER
    -0.78
    ter
    -0.77
    ener
    -0.76
    AndEndTag
    -0.76
    ENER
    -0.76
    oter
    -0.73
    POSITIVE LOGITS
    Rhestr
    0.63
     Blast
    0.51
    AxisAlignment
    0.50
    例文
    0.48
    HOLD
    0.47
     détruire
    0.46
    Discography
    0.45
     Hock
    0.45
     cancha
    0.45
    Blast
    0.45
    Activations Density 0.987%

    No Known Activations