© 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. 8050
    Prev
    Next
    INDEX
    Explanations

    words related to chemistry, filtration, and categorization.

    oai_token-act-pair · gemini-2.0-flash

    Scientific and technical 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_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
    ed
    -1.30
    ist
    -1.19
    ized
    -1.10
    ists
    -1.09
    able
    -1.09
    ize
    -1.09
    ian
    -1.09
    ities
    -1.09
    i
    -1.05
    ie
    -1.04
    POSITIVE LOGITS
    ת
    0.37
    ة
    0.36
    로
    0.35
    orium
    0.34
    ingale
    0.32
     للاسماء
    0.32
    équi
    0.31
    enderror
    0.30
    snail
    0.30
    なるほど
    0.30
    Activations Density 3.488%

    No Known Activations