© 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. 6538
    Prev
    Next
    INDEX
    Explanations

    words and phrases used when telling a story

    oai_token-act-pair · gemini-2.0-flash

    statements and conversations

    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
     Efq
    -1.38
     itſelf
    -1.23
     Monfieur
    -1.23
     myſelf
    -1.21
     Theſe
    -1.10
     ―――――
    -1.08
    BibitemShut
    -1.07
     Мексичка
    -1.07
    bibfield
    -1.04
     Jefus
    -1.04
    POSITIVE LOGITS
    ha
    0.47
    ma
    0.43
    us
    0.43
    ic
    0.42
    he
    0.42
    om
    0.42
    co
    0.42
    ce
    0.41
    tr
    0.41
    va
    0.40
    Activations Density 2.651%

    No Known Activations