© 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. 7773
    Prev
    Next
    INDEX
    Explanations

    HTML tags, certain words related to narrative and politics, and the "fil" in filename

    oai_token-act-pair · gemini-2.0-flash

    Code/filenames

    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
    xase
    -0.51
    atá
    -0.47
    LikeLike
    -0.45
    raska
    -0.41
    UCA
    -0.41
    ushort
    -0.40
     "",
    -0.40
     Hod
    -0.40
    ranean
    -0.39
     Scotia
    -0.39
    POSITIVE LOGITS
    eload
    0.66
    ecap
    0.65
    EClass
    0.64
    eliner
    0.63
    edb
    0.62
    èdia
    0.60
    esinde
    0.59
    elin
    0.59
    epro
    0.58
    edata
    0.58
    Activations Density 13.818%

    No Known Activations