© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7773
    Prev
    Next
    INDEX
    Explanations

    the word "lower" or "higher" in the context of comparisons

    oai_token-act-pair · gemini-2.0-flash

    lower

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    othesis
    -1.12
     Houſe
    -1.04
     Anſ
    -1.04
    ividual
    -1.02
     Theſe
    -1.02
     autorytatywna
    -0.99
    ENEFITS
    -0.97
     télécharge
    -0.96
     Diſ
    -0.95
     itſelf
    -0.95
    POSITIVE LOGITS
    ba
    0.64
    g
    0.60
    du
    0.59
    '];
    0.58
    co
    0.58
    ')->
    0.58
    ri
    0.57
    ar
    0.57
     ins
    0.57
    '};
    0.57
    Activations Density 1.339%

    No Known Activations