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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10744
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to companies, people, and organization names in the context of technology, business, and security.

    oai_token-act-pair · gemini-2.0-flash

    Positive adjectives

    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
    MigrationBuilder
    -0.81
     مشين
    -0.75
    ########.
    -0.65
    +#+
    -0.63
    ftagPool
    -0.60
    󠁴
    -0.57
     oprot
    -0.54
    elemField
    -0.54
    fjspx
    -0.54
    ::::::::
    -0.53
    POSITIVE LOGITS
     Genius
    0.59
     Virtue
    0.56
     Kuj
    0.54
     Guinness
    0.53
     Hyal
    0.53
     Legendary
    0.52
     Bounty
    0.52
     Proud
    0.52
     Nian
    0.52
     Humble
    0.52
    Activations Density 4.648%

    No Known Activations