Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14720
    Prev
    Next
    INDEX
    Explanations

    Icelandic references in a critical context

    oai_token-act-pair · gemini-2.0-flash

    Icelandic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    mybatisplus
    -0.75
     AssemblyCulture
    -0.57
    CHOR
    -0.56
    Chor
    -0.54
     Chor
    -0.52
     Cours
    -0.50
     Micho
    -0.50
    WriteBarrier
    -0.50
    chappen
    -0.50
     Chichester
    -0.47
    POSITIVE LOGITS
    hending
    0.54
     Namely
    0.53
    nellement
    0.51
    olars
    0.49
    <bos>
    0.49
     defaultstate
    0.49
    pina
    0.49
    colgroup
    0.48
    ulties
    0.48
    isure
    0.48
    Activations Density 0.454%

    No Known Activations