© 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. 11086
    Prev
    Next
    INDEX
    Explanations

    text related to lithium-ion batteries

    oai_token-act-pair · gemini-2.0-flash

    Batteries and chemical processes

    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
     Roskov
    -0.65
     Мексичка
    -0.64
     فريبيس
    -0.60
     betweenstory
    -0.56
    ArrowToggle
    -0.56
     esternos
    -0.55
     мәкал
    -0.54
     الاطلاع
    -0.53
     AssemblyVersion
    -0.53
    mbggenerated
    -0.52
    POSITIVE LOGITS
    addis
    0.55
    interopRequire
    0.50
     αγ
    0.48
     TestBed
    0.48
    SetOutput
    0.47
    igraph
    0.47
     Gere
    0.47
    MathML
    0.46
    complexContent
    0.45
     fjer
    0.45
    Activations Density 12.757%

    No Known Activations