© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7353
    Prev
    Next
    INDEX
    Explanations

    short words such as prepositions and articles in the middle of sentences

    oai_token-act-pair · gemini-2.0-flash

    variants of "he"

    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
     propOrder
    -0.80
     fallu
    -0.65
    interopRequire
    -0.60
    opsida
    -0.60
    IndentedString
    -0.58
    stdc
    -0.56
    Autoritní
    -0.53
     فريبيس
    -0.53
    Przypisy
    -0.52
    utilisons
    -0.52
    POSITIVE LOGITS
     he
    3.94
    He
    2.41
    he
    2.34
     он
    2.20
     He
    2.11
    他
    1.71
     him
    1.70
    彼は
    1.69
     그는
    1.67
     він
    1.65
    Activations Density 17.230%

    No Known Activations