© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3165
    Prev
    Next
    INDEX
    Explanations

    geographic place names and words associated with land management and location

    oai_token-act-pair · gemini-2.0-flash

    location

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    稳
    -0.43
    und
    -0.42
    getLogin
    -0.41
    ·
    -0.40
    v
    -0.40
    OH
    -0.39
    дак
    -0.39
    受け
    -0.39
    ou
    -0.38
    7
    -0.37
    POSITIVE LOGITS
    CppMethod
    0.90
    Vidite
    0.88
    KURZBESCHREIBUNG
    0.83
    EDEFAULT
    0.81
    SharedDtor
    0.75
    ChildScrollView
    0.75
    Autoritní
    0.72
    تقاوى
    0.72
    AxisAlignment
    0.72
     חיצוניים
    0.71
    Activations Density 1.434%

    No Known Activations