© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10712
    Prev
    Next
    INDEX
    Explanations

    first person pronouns, dates, and the occasional number.

    oai_token-act-pair · gemini-2.0-flash

    expressing personal opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     للاسماء
    -0.62
    Personendaten
    -0.57
    ThroughAttribute
    -0.52
    principalTable
    -0.52
    ⓧ
    -0.50
    Източници
    -0.48
     الدولى
    -0.47
    issor
    -0.46
     vulgares
    -0.45
    tieth
    -0.45
    POSITIVE LOGITS
     be
    3.09
    be
    2.02
    Be
    1.99
     Be
    1.86
     soient
    1.65
     BE
    1.59
    BE
    1.30
     sejam
    1.28
     aient
    1.26
     siano
    1.20
    Activations Density 15.519%

    No Known Activations