© 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. 6637
    Prev
    Next
    INDEX
    Explanations

    the letters "H" or "Ho" in a large variety of contexts, sometimes preceded by another letter.

    oai_token-act-pair · 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
     H
    -0.88
    H
    -0.77
     HM
    -0.70
     Hn
    -0.70
    /*
    -0.69
     Har
    -0.66
    HM
    -0.62
     Hac
    -0.60
    Har
    -0.59
     Her
    -0.59
    POSITIVE LOGITS
    h
    0.85
    he
    0.77
    hout
    0.72
    hers
    0.72
    hine
    0.69
    hé
    0.68
    hhh
    0.67
    hh
    0.67
    hland
    0.66
    hijo
    0.66
    Activations Density 1.268%

    No Known Activations