© 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. 4371
    Prev
    Next
    INDEX
    Explanations

    descriptions of an injured or messy person or thing

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
     mess
    -1.55
     messy
    -1.45
     Mess
    -1.35
     messes
    -1.33
     dirty
    -1.30
    mess
    -1.30
     mud
    -1.20
     Dirty
    -1.20
    Mess
    -1.17
     MESS
    -1.14
    POSITIVE LOGITS
     ejus
    0.51
     quæ
    0.51
     avoient
    0.47
    期刊论文
    0.45
     الدولى
    0.45
    ῖς
    0.45
     पाल
    0.45
     klaus
    0.44
    +#+
    0.44
     مواليد
    0.44
    Activations Density 2.447%

    No Known Activations