© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4112
    Prev
    Next
    INDEX
    Explanations

    words and phrases involving hypothetical situations, possibilities, and requests

    oai_token-act-pair · gemini-2.0-flash

    say "be"

    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
    Архівовано
    -0.56
    CloseOperation
    -0.54
     is
    -0.50
    getMenuInflater
    -0.47
    skraft
    -0.46
     là
    -0.45
    Sucesor
    -0.45
    исленность
    -0.44
    rítica
    -0.44
    ]");
    -0.44
    POSITIVE LOGITS
     Be
    1.39
    be
    1.38
    Be
    1.35
     BE
    1.24
    BE
    1.23
     bo
    0.96
     bea
    0.90
     b
    0.89
     beryllium
    0.81
    bé
    0.81
    Activations Density 6.306%

    No Known Activations