© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 2342
    Prev
    Next
    INDEX
    Explanations

    words relating to giving information or people being informative

    oai_token-act-pair · gemini-2.0-flash

    formal reports and documentation

    np_token-act-pair-logits · gpt-4o-mini

    official statements/reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    GenerationType
    -0.60
     estimés
    -0.58
    hould
    -0.54
    ]--;
    -0.53
     desist
    -0.52
     caress
    -0.52
    createComponent
    -0.52
    المشاركات
    -0.50
     postre
    -0.50
    notifyListeners
    -0.50
    POSITIVE LOGITS
    出版年
    0.83
    windowFixed
    0.59
    TintMode
    0.56
     ModelExpression
    0.56
     åt
    0.55
     MenuView
    0.55
     <<<<<<<<<<<<<<
    0.54
     Wicidata
    0.54
    warted
    0.53
    OGND
    0.52
    Activations Density 1.246%

    No Known Activations