© 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. 13002
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases and other characters within science and academic literature

    oai_token-act-pair · gemini-2.0-flash

    dash

    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
    už
    -0.53
    )».
    -0.52
    utenant
    -0.51
    YARD
    -0.48
    )";
    -0.48
    Срок
    -0.47
    stash
    -0.47
    upvote
    -0.47
    nought
    -0.47
    dues
    -0.47
    POSITIVE LOGITS
     AttributeSet
    0.56
     nakalista
    0.56
    PYX
    0.55
     ContentValues
    0.52
    parsedMessage
    0.52
     cucchiaio
    0.51
    はじめに
    0.50
     viewDidLoad
    0.49
     Rukh
    0.49
    لينكات
    0.49
    Activations Density 9.291%

    No Known Activations