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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1344
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear frequently and are related to making conclusions

    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
     Grecs
    -0.57
     âmes
    -0.57
     circonstances
    -0.56
     autorités
    -0.56
     idées
    -0.55
     modalités
    -0.54
     états
    -0.54
     pouvoirs
    -0.54
     unités
    -0.53
     goûts
    -0.53
    POSITIVE LOGITS
    rogels
    0.85
     glaciers
    0.85
     sarees
    0.82
     Cruises
    0.82
     mortgages
    0.81
     migraines
    0.80
     Tattoos
    0.79
     Cupcakes
    0.79
     ETFs
    0.79
     droughts
    0.79
    Activations Density 38.444%

    No Known Activations