© 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. 5528
    Prev
    Next
    INDEX
    Explanations

    seemingly random numbers, often years, interspersed with other characters

    oai_token-act-pair · gemini-2.0-flash

    code snippets or legal text

    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
     Theſe
    -0.26
     zelve
    -0.22
     varandra
    -0.19
     feroit
    -0.18
     avoient
    -0.18
     étoit
    -0.17
     auroit
    -0.17
     pouvoit
    -0.16
     Efq
    -0.16
     étoient
    -0.15
    POSITIVE LOGITS
    </strong>
    0.73
    ↵↵
    0.71
    ↵
    0.71
    
    0.69
    </em>
    0.69
    .
    0.69
    0.69
     Sal
    0.68
    sa
    0.67
    ⓘ
    0.67
    Activations Density 4.274%
    No Known Activations