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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10174
    Prev
    Next
    INDEX
    Explanations

    the word "in" in a variety of contexts, sometimes close to words like "is", "at", "fact" or conjunctions from the first few words of sentences.

    oai_token-act-pair · gemini-2.0-flash

    in

    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
     fact
    -0.69
    fact
    -0.65
     Fact
    -0.59
    Fact
    -0.57
     reality
    -0.54
    SPATH
    -0.52
     thực
    -0.52
    reality
    -0.49
    GEBURTSDATUM
    -0.49
     fakta
    -0.48
    POSITIVE LOGITS
    elemField
    0.61
     in
    0.59
     Roskov
    0.56
     Riproduzione
    0.55
    RefNanny
    0.54
    الدراسه
    0.54
    ωνα
    0.54
    Personendaten
    0.54
     heilig
    0.53
     Houſe
    0.53
    Activations Density 7.732%

    No Known Activations